@proceedings{lrec:sign-lang:26, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, title = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/2026.signlang-1.pdf}, doi = {10.63317/4zjm486botgq} } @inproceedings{barbera:26041:sign-lang:lrec, author = {Barber{\`a}, Gemma and Broto Clemente, In{\'e}s and Vinaixa Rosell{\'o}, Xavier and Cassany Viladomat, Roger}, title = {Capturing Methodology for Generating Synthetic and {3D} Training Data in {Catalan} {Sign} {Language} ({LSC}): The Case of Verbal Agreement}, pages = {1--9}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26041.html}, doi = {10.63317/3g3si7nypow8}, abstract = {This paper proposes a hybrid methodology to generate high-quality synthetic data. Unlike other approaches based purely on generative Artificial Intelligence, which may suffer from hallucinations or inconsistent movements, this project uses 3D biomechanics and kinematics algorithms that enforce the anatomical constraints of the human body to ensure physically plausible movements. The aim of this research is to demonstrate that it is possible to synthetically expand the dataset. In particular, this paper focuses on verb agreement, a grammatical domain which is known for its morphological and articulatory complexity. By concentrating on the possible configurations of the movements in signing space when expressing different person agreeing verbal forms, we aim to capture real movements to extract physical parameters and apply them as logical rules ---similar to those of a video game engine--- to automatically synthesize thousands of new conjugations from infinitives with complete anatomical precision. Beyond spatial conjugation, the methodology further augments data through procedural variation of prosody and body morphology.} } @inproceedings{bassomadjoukeng:26037:sign-lang:lrec, author = {Basso Madjoukeng, Ariel and Poitier, Pierre and Kenmogne, Belise Edith and Couplet, Ad{\'e}la{\"i}de and Leleu, Margaux and Fr{\'e}nay, Beno{\^i}t}, title = {Leveraging Unannotated Sign Language Data via a Robust Data Augmentation Method for Contrastive Representation Learning}, pages = {10--16}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26037.html}, doi = {10.63317/4qnrmhtbv9cz}, abstract = {Contrastive learning is a deep learning paradigm that allows the learning of useful representations without annotations. In many fields, including sign language recognition (SLR), contrastive approaches have proven to be very effective for developing pretrained models. To learn representations, they generate augmented variants of an instance through augmentation techniques and then maximize their similarities. The quality of the learned representations is strongly correlated with the augmentations used during training. In several fields, specialized augmentations have been developed and adopted. However, in SLR, we observed two trends: contrastive-based SLR approaches often rely on augmentations that are not realistic for the application (e.g., vertical flip, excessive rotations); specialized augmentation methods lack robustness. Hence, when they are used as a starting point for contrastive algorithms, the learned representations are often irrelevant, and sometimes sensitive. These issues considerably affect the accuracy of SLR models on downstream tasks. In response, this paper proposes a robust augmentation method specially designed for contrastive approaches applied to SLR. The results show an improvement in accuracy during linear evaluation and semi-supervised learning with only 30{\%} of annotations.} } @inproceedings{battisti:26034:sign-lang:lrec, author = {Battisti, Alessia and Tissi, Katja and Sidler-Miserez, Sandra and Ebling, Sarah}, title = {The {SMILE} {Continuous} {DSGS} {Corpus}: A Resource for Longitudinal Exploration of Continuous {Swiss} {German} {Sign} {Language}}, pages = {17--30}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26034.html}, doi = {10.63317/3x4j9f32vbb9}, abstract = {This paper presents the SMILE Continuous DSGS Corpus, a longitudinal dataset that allows for investigating how hearing adults acquire Swiss German Sign Language as a second language. It includes recordings of sign language learners and native signer controls collected at four points over a period of 18 months and annotated for manual and non-manual components, errors, and sentence-level acceptability. The resource provides high-quality, synchronized video suitable for both linguistic and automatic sign language processing research, for example, supporting studies of interlanguage development and training of automatic sign language recognition models. We present here an exploratory analysis of the learner subcorpus using Bayesian mixed-effects modeling. The corpus and accompanying annotations are available for research purposes under a Creative Commons license (CC BY-NC-SA 4.0).} } @inproceedings{boddu:26033:sign-lang:lrec, author = {Boddu, Raviteja and Vieira Leite, Guilherme and Lopes da Silva, Joed and Benetti, {\^A}ngelo and Barbieri, Isabela and de Melo Afonso, Nat{\'a}lia and Santos, Thyago and Pedrini, H{\'e}lio and Ven{\^a}ncio Barbosa, Felipe and De Martino, Jos{\'e} Mario and Georges, Munir and Zimmer, Alessandro}, title = {The {In-Car} {Sign} {Language} {Corpus} ({ICSL}): A Multi-Modal Resource for Constrained-Space Sign Language Recognition}, pages = {31--41}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26033.html}, doi = {10.63317/58vz3o8c8yc7}, abstract = {This paper addresses the challenges of using sign language within shared mobility services, such as taxis, carpools, or ride-sharing platforms. The use of sign language recognition (SLR) in real-world, confined environments, specifically vehicle interiors remains largely unexplored. To motivate research in this area, we present the In-Car Sign Language (ICSL) dataset for Brazilian Sign Language (Libras), with the long-term goal of improving public transport accessibility for the Deaf and Hard-of-Hearing community. The dataset consists of: (1) high-precision laboratory motion capture (MoCap) data to establish an idealized linguistic baseline and (2) real-world multi-modal in-car recordings captured using a 2D camera and 3D Time-of-Flight sensors. The dataset provides a basis for comparative analyses between synthesized signing avatar animations and recorded real signing interpreter videos, which enable future research into robust "in-the-wild" SLR models and domain adaptation. We describe in detail the use cases, the setup, the data collection protocol, and the metadata structure of the corpus. In total, we recorded a multimodal dataset exceeding 1.5 million frames, comprising the synchronized multimodal streams described above featuring Libras users across various in-car scenarios. The corpus is provided with gloss annotation of lexical signs and non-lexical sign language elements specially designed to support the training and evaluation of deep neural networks for constrained space recognition. In-vehicle signing offers a technically significant example of a constrained, occluded, and non-frontal environment. While recognizing the diverse communication strategies already employed by the Deaf community, identifying automotive-specific limitations provides a useful stepping stone for research into enhancing in-car accessibility and passenger quality of life.} } @inproceedings{borstell:26004:sign-lang:lrec, author = {B{\"o}rstell, Carl}, title = {Seeing Who Is Signing and With Which Hand}, pages = {42--50}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26004.html}, doi = {10.63317/2b7gxto5x6rs}, abstract = {This study is a computer vision analysis of 4.5 hours of video data from 40 signers in the Swedish Sign Language Corpus, aiming to evaluate the reliability of classifying 1) who the main signer is at any given time during dyadic conversation, and 2) the dominant hand (i.e., handedness) of each signer. First, the distance moved by the hands of each signer is used to compare the manual activity between a) the two signers to determine whose hands are more active, and b) the hands of each signer to determine which hand is more likely to be dominant. Second, the height of the hands is used to compare their prominence in signing space between a) the two signers to determine whose hands are more prominent, and b) the hands of each signer to determine which hand is more likely to be dominant. The results show that while both distance and height approaches can reliably classify -- individually or combined -- the main signer in any segment of a conversation, the height approach is better at determining the overall handedness (right- or left-dominant) of signers. For the handedness classification, the optimal method turns out to be a two-step approach, first classifying the main signer per segment, then using only signer-relevant segments to classify handedness.} } @inproceedings{brown:26026:sign-lang:lrec, author = {Brown, Matt and Ranum, Oline and Fish, Edward and Proctor, Heidi and Woll, Bencie and Bowden, Richard and Cormier, Kearsy}, title = {{SignGPT} and the {Visual} {Language} {Toolkit}}, pages = {51--60}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26026.html}, doi = {10.63317/5ez54d2x8yos}, abstract = {SignGPT's Visual Language Toolkit (VLTK) aims to remove fundamental barriers to large scale sign language modelling by developing data-driven, linguistically grounded methods for continuous sign language recognition. We first identify fundamental issues around the ecological validity of potential data sources (e.g. broadcast media with interpreted signing or captions, scraping of social media). We contrast these with the currently highly resource-intensive development of curated sign language corpora based on linguistic principles. The VLTK addresses this scarcity of high quality sign language data by providing semi-automated glossing and other recognition tools, driving large scale corpus expansion without sacrificing linguistic principles. Unlike prior systems that rely on sparse glossing, the project integrates dense temporal annotation, non-manual and non-lexical feature tracking, and transformer-based architectures to capture the multimodal and spatial structure of signing. By aligning machine vision innovation with linguistic insights and community-embedded evaluation, SignGPT establishes a foundation for robust and extensible sign language models.} } @inproceedings{bulla:26021:sign-lang:lrec, author = {Bulla, Jan and Kimmelman, Vadim}, title = {Processing Kinematics of Nonmanual Markers in {R}}, pages = {61--70}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26021.html}, doi = {10.63317/35fyd7w2c7sm}, abstract = {Nonmanual markers, such as head and eyebrow movements, eye blinks, and mouth shapes, are an important part of natural languages, both spoken and signed. Recent developments in computer vision have made it possible to extract facial and body landmark positions, as well as head-rotation measures, from 2D video recordings, which can be further processed to analyse the kinematics of nonmanual articulators. In this paper, we present an R-based workflow for processing raw outputs of computer vision toolkits with the goal of producing reliable and interpretable kinematic measurements of nonmanual articulators.} } @inproceedings{chan:26055:sign-lang:lrec, author = {Chan, Frederick and Levow, Gina-Anne and Cheng, Qi}, title = {A Small Model for Big Articulators: Sign Language Detection With a Tiny Machine Learning Model}, pages = {71--79}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26055.html}, doi = {10.63317/4s65esyxekat}, abstract = {This paper introduces a small (1,013 parameter) machine learning model for sign language detection in videos of isolated American Sign Language (ASL) signs. Our model aims to alleviate the time-consuming nature of producing sign clips for psycholinguistic study stimuli, sign dictionaries, and sign databases. Given a video where the signer starts from a resting position, signs a sign, and returns to the resting position for an arbitrary number of repetitions, the model detects frames in which signing occurs that can be used to segment video into clips of individual signs. We train and evaluate our model on data with precise coding of signing onset and offset from ASL-LEX 2.0, so that our model's annotations are suitable for psycholinguistics research. The model works on both real signs and pseudosigns, two types of stimuli needed for certain psycholinguistic studies. Our model's small size compared to the state-of-the-art (100K parameters or more) enables quick, bulk processing even on resource-constrained hardware. It achieves this by computing Instantaneous Visual Change (IVC), a 1D measure of changes in brightness in the input video, extracting features from the IVC-over-time signal with a convolution, and classifying the video frames as signing or non-signing with three neural layers.} } @inproceedings{czehmann:26064:sign-lang:lrec, author = {Czehmann, Vera and Yazdani, Shakib and Hamidullah, Yasser and Nunnari, Fabrizio and Avramidis, Eleftherios}, title = {"A Sacred Bird Called the Phoenix". Auditing the most-used Parallel Corpus for {German} {Sign} {Language} Recognition and Translation}, pages = {80--92}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26064.html}, doi = {10.63317/3xftynuw7i5c}, abstract = {This paper presents an empirical audit of the widely used RWTH-PHOENIX-2014T corpus, examining its suitability as a benchmark for sign language recognition and translation. Through human annotation of the training set and extensive sign-to-text back translation of the test set, we provide detailed statistics that indicate substantial quality issues, including information loss and lexical errors. Automatic scores comparing human sign-to-text back translations to the original speech transcribed references are remarkably low, suggesting strong translationese effects and substantial paraphrasing, revealing limitations of lexical metrics in adequately scoring translation quality. Replacing the original speech-transcribed references with human sign-to-text back translations while scoring existing sign language translation systems reveals the lack of robustness of system evaluation with lexical metrics against this test set. Our findings highlight risks associated with relying on this corpus for model evaluation and call for more rigorous, linguistically grounded evaluation practices in sign language technology research. The back-translated test set and error annotations are made publicly available.} } @inproceedings{dai:26006:sign-lang:lrec, author = {Dai, Zixuan and Sako, Shinji}, title = {Diffusion-Based {3D} Sign Language Motion Anonymization: A Feasibility Study on Balancing Identity Confusion and Semantic Preservation}, pages = {93--99}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26006.html}, doi = {10.63317/4nrz6i8vbmt2}, abstract = {Sign language motions contain individual-specific kinematic features. As the engineering applications of sign language become more widespread, privacy protection of sign language data has emerged as a new challenge. This paper proposes a diffusion model-based approach for sign language motion anonymization. The proposed framework combines conditional diffusion processes with adversarial training to transform identity features while preserving semantic information. For the design and preliminary validation of the proposed model, we conduct a proof-of-concept experiment using a subset of 22 signers from the ASL100 dataset of WLASL, which demonstrates the feasibility of the proposed approach for sign language anonymization.} } @inproceedings{devos:26002:sign-lang:lrec, author = {De Vos, Liesbet and Meurant, Laurence and Van Eecke, Paul and Beuls, Katrien}, title = {{GeoQuery-LSFB}: A {French} {Belgian} {Sign} {Language} Corpus with Procedural Semantic Annotations}, pages = {100--112}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26002.html}, doi = {10.63317/3beia2n27dp3}, abstract = {Procedural semantic representations describe the meaning of natural language expressions in terms of computer programs that can be evaluated against images, databases, knowledge graphs or other external resources. While resources annotated with procedural semantic representations already exist for a variety of spoken languages, such resources are still lacking entirely for signed languages. In this paper, we introduce GeoQuery-LSFB as a signed language extension to the multilingual GeoQuery corpus. Concretely, we have complemented each procedural semantic annotation from the original corpus with a corresponding French Belgian Sign Language (LSFB) expression that was phonetically transcribed from video recordings following the HamNoSys convention and annotated with French ID-glosses. The GeoQuery-LSFB corpus constitutes a new resource for a low-resource language and offers for the first time the possibility to study, from an onomasialogical perspective, a signed language along a diverse variety of spoken languages.} } @inproceedings{dimou:26029:sign-lang:lrec, author = {Dimou, Athanasia-Lida and Goulas, Theodoros and Tsatali, Marianna and Ntova, Tarsita and Hoffmann-Lamplmair, Doris and Fotinea, Stavroula-Evita and Efthimiou, Eleni and Teichmann, Birgit and Tsolaki, Magda and Atkinson, Joanna and Woll, Bencie}, title = {The {De-Sign} Platform: An Online Psychometric Tool for Dementia Screening of Deaf Older Adults in two Sign Languages, {GSL} and {{\"O}GS}}, pages = {113--119}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26029.html}, doi = {10.63317/35c4iweidxm2}, abstract = {This article presents the De-Sign platform, a web-based psychometric tool specifically designed for screening dementia in Deaf older adults (50+) who use Austrian Sign Language and Greek Sign Language hereinafter {\"O}GS and GSL respectively. The limited access to dementia services for these populations is primarily attributed to a scarcity of healthcare professionals fluent in sign language. Hence, enhancing access to relevant diagnostic services has become a priority. Currently, there is a significant lack of screening tools specifically developed to identify early signs of dementia that are compatible with national sign languages. To address this issue, the De-Sign Erasmus+ (2022-2025) project has employed suitable psychometric instruments that are adapted to the cultural contexts and linguistic norms of Deaf communities in Austria and Greece. The only existing Cognitive Screening Test (CST) for British Sign Language (BSL), used for diagnosing dementia in Deaf older adults, was initially adapted from English by Atkinson et al. (2015). The De-Sign platform hosts a cognitive screening test in {\"O}GS and GSL. Both were linguistically and culturally adapted from the BSL-CST test, providing two web-based versions of a psychometric tool that enables dementia screening within these populations.} } @inproceedings{duppen:26049:sign-lang:lrec, author = {Duppen, Yves A. and De Sisto, Mirella and Mavridou, Ifigeneia and Brown, Phillip and Lepp, Lisa and Shterionov, Dimitar}, title = {Feature Analysis of {MoCap} Data for Optimised Sign Language Processing}, pages = {120--128}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26049.html}, doi = {10.63317/4e3o6m3ntvt3}, abstract = {Despite the rapid advances in AI and its impact on machine translation (MT), when it comes to sign language (SL) processing and MT, there is a big bottleneck -- the lack of substantial quantities of quality signed data suitable for developing SLMT models. Marker-based motion capturing (MoCap) is a technique for tracing and recording the body movements (including hands and figures) in 3D space with high precision and has been widely used in SL research. MoCap data is of high representative accuracy, making it very suitable for analysing movement patterns and articulatory features. However, it is also very complex -- a recording of a single sign may contain more than 240 entries over 156 features making it difficult for processing. In this paper we analyse MoCap data aiming to understand which captured features are of high importance. Consecutively, we optimise the MoCap data representation, reducing the number of features, and assess how this feature- reduced data impacts sign classification task. We organise MoCap features based on their importance and show how models trained on feature-reduced representations outperform those developed on the complete feature set.} } @inproceedings{fabre:26016:sign-lang:lrec, author = {Fabre, Diandra and Lascar, Julie and Halbout, Julie and Vartampetian, Markarit}, title = {Leveraging Text-side Augmentation For Sign Language Translation}, pages = {129--139}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26016.html}, doi = {10.63317/53aordwh6sf8}, abstract = {Sign language translation faces significant challenges due to the scarcity of annotated data and the inherent complexity of sign languages. This paper presents a method to improve sign-to-text translation models by augmenting data on the text side. We conduct experiments using two state-of-the-art models on two publicly available datasets: PHOENIX-2014T for German Sign Language and Mediapi-RGB for French Sign Language. Our main contributions are : (1) augmenting the training sets of both datasets on the text side using a generative model, (2) evaluating the impact of paraphrasing on BLEU and BLEURT scores, and (3) analyzing the impact of paraphrasing on translation outputs. We observed a significant improvement in translation for both languages. This suggests that adding variability to the training dataset through paraphrasing can lead to better generalization of the models. These results are comparable to state-of-the-art methods that use more complex approaches, such as Visual-Language fine-tuning, to improve translation.} } @inproceedings{fernandezsoneira:26048:sign-lang:lrec, author = {Fern{\'a}ndez Soneira, Ana and Bao-Fente, Mar{\'i}a C. and Gonz{\'a}lez-Montesino, Rayco H. and B{\'a}ez Montero, Inmaculada C.}, title = {The Construction of the {CORALSE} Corpus, Now and Beyond: A Tool for Documenting {Spanish} {Sign} {Language}}, pages = {140--147}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26048.html}, doi = {10.63317/5aiop98n7wa4}, abstract = {The main objective of this paper is to present the experience of building the CORALSE corpus and to discuss the challenges that arise when attempting to provide a comprehensive description of a sign language. To this end, we address the following questions, drawing on the data obtained in the completed phases of the CORALSE project as well as on the foundational principles guiding the project's third phase. THE CORALSE CORPUS TODAY: How have we developed a linguistic corpus of sign language?, What steps have we taken in developing the CORALSE corpus?, Which informants have we recorded and what criteria have guided their selection? THE CORALSE CORPUS IN THE FUTURE: Which (native) languages do we prioritise when selecting informants?, How do the perspectives of reference signers, interpreters, educators, and psycholinguists contribute to a more complete understanding of a sign language? Corpus linguistics is understood as a set of methodologies designed to study language through collections of digitised texts. Its development over recent decades---initially driven by advances in computing and, subsequently, by the emergence of the internet---represents one of the most significant transformations in contemporary linguistic research. The projects CORALSE: Annotated Inter-university Corpus of Spanish Sign Language and Textual Typology, Registers and Styles in Spanish Sign Language: New Data for the Expansion of the CORALSE Corpus adopt a corpus linguistics approach to collect, analyse and describe a representative sample of Spanish Sign Language (LSE). We also reflect on the types of linguistic data that are truly necessary to document the actual use of Spanish Sign Language.} } @inproceedings{ferrara:26005:sign-lang:lrec, author = {Ferrara, Lindsay}, title = {The Community and Ethics Shaping the {Norwegian} {Sign} {Language} Corpus}, pages = {148--154}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26005.html}, doi = {10.63317/5mp34ud7f5bp}, abstract = {Recently, the Norwegian Sign Language Corpus has been published, and it includes language data from over 100 signers from around Norway. Collecting and building such multimodal signed language corpora have important implications for both research and deaf communities. However, consideration is needed to protect the personal nature of signed language data, while also making a long-term resource that is as accessible as possible to various community, research, and professional stakeholders. In addition, the potential exploitation of corpus resources by commercial and other interests, which are not necessarily aligned with the deaf community itself, must also be deliberated. Here, these seemingly opposing issues and the ethics that surround them are discussed. Current best practices in Open Science (including FAIR and CARE data principles), along with ethical discussions raised by scholars working, for example, in Deaf Studies, are shown to be important in navigating this complex research data landscape.} } @inproceedings{fiedler:26038:sign-lang:lrec, author = {Fiedler, Anike and Schulder, Marc and Bleicken, Julian and Herrmann, Annika}, title = {Generations in the {DGS} {Corpus}: Evolving Outreach Activities and Cross-Generational Stories on Social Media in a Long-Term Corpus Project}, pages = {155--163}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26038.html}, doi = {10.63317/4owc5cgudibc}, abstract = {Social media has become a powerful tool for research projects, community outreach, science communication, and to recruit participants. Due to its differences to traditional media and presentation modes, it provides a particular focus on producing very concise content that is entertaining and accessible while staying informative. In this paper, we describe how the long-term project DGS-Korpus, creators of a corpus and dictionary of German Sign Language, evolved its outreach strategies over time. One unique aspect of its unusually long project run-time of nineteen years is that it has involved several cases of multiple family members participating in the project at different points in time, resulting in cross-generational participation. The paper describes how the project's social media campaign uses these cross-generational connections to illustrate important aspects of the project, such as its relevance for cultural heritage and language identity, the different ways that members of the German deaf community were and are involved in the project, and its relevance to interpersonal connections.} } @inproceedings{filhol:26045:sign-lang:lrec, author = {Filhol, Michael and Martinod, Emmanuella}, title = {Formalising Sign Language Depiction, Characterising Categories and Measuring Iconicity with {AZee}}, pages = {164--173}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26045.html}, doi = {10.63317/5a8jvximd4ki}, abstract = {This paper deals with depiction in (French) Sign Language, the formal account AZee can provide, and how it compares, validates or simplifies the linguistic notions of classifiers and iconic structures. It reports on a partial encoding work on "Mocap1", a corpus with a high density of depicting structures, following the same method that led to the first AZee reference corpus "40 br{\`e}ves". The approach does not postulate classifiers or iconic structures as entities separate from lexical signs, and nonetheless manages to model the corpus data. We discuss the entailed possibility to rediscover some of the useful categories, and if so define them from AZee's premises. We also specify how a formal metric can be specified to measure iconicity in signed data. While this paper is of linguistic interest as it compares to existing theories, it also provides a concrete step to covering depicting discourse with AZee, therefore enable automatic SL animation of depiction.} } @inproceedings{delagarza:26039:sign-lang:lrec, author = {de la Garza, Lorena and Halbout, Julie and Lascar, Julie and Mart{\'i}nez-Guevara, Niels and Curiel, Arturo and Gouiff{\`e}s, Mich{\`e}le and Braffort, Annelies}, title = {Extracting Signs from Weakly Aligned Sign Language Corpora: A Study on {LSF} and {LSM}}, pages = {174--183}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26039.html}, doi = {10.63317/38kfot52b4dz}, abstract = {This paper presents a framework for the automatic annotation of sign language data across different recording conditions, including original and interpreted content. The proposed approach integrates weak alignment, sign segmentation, and multiple instance learning with a contrastive loss. The resulting annotations are subsequently refined and filtered to enhance their reliability. Our method was applied to two historically related sign languages, French Sign Language (LSF) and Mexican Sign Language (LSM). This led to the creation of two signaries, comprising approximately 2k categories in LSF (25k occurrences) and 41 categories in LSM (1k occurrences). Both resources provide valuable support for future research in artificial intelligence and linguistics, particularly for comparative analyses between the two languages. A seminal analysis is presented as part of this paper.} } @inproceedings{gibet:26046:sign-lang:lrec, author = {Gibet, Sylvie and Reverdy, Cl{\'e}ment and Marteau, Pierre-Fran{\c c}ois}, title = {An Annotation Formalism for a {French--LSF} Bilingual Corpus Supporting Sign Language Generation}, pages = {184--192}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26046.html}, doi = {10.63317/3fpfgrum7nxo}, abstract = {This paper introduces an annotation formalism for bilingual corpora of written French and French Sign Language (LSF), based on a manually-produced, expert transcription of LSF video data. The formalism captures the grammatical specificities of LSF, including spatial and iconic mechanisms, while explicitly encoding features that support motor programs for animated signing avatars. We propose a parameterized gloss-based approach, called PGloss-LSF, which integrates syntactic and semantic structures alongside motion features critical for accurate sign synthesis. We illustrate the framework with examples drawn from our bilingual corpus. The annotation process is incremental, ensuring internal consistency and computational tractability through a two-step evaluation: a qualitative assessment aligning generated signs with the annotation language, and a quantitative evaluation via automatic translation using large language models. By bridging the linguistic specificities of sign language with the computational requirements of sign synthesis, this work advances the integration of sign language corpora into multilingual resources and contributes to the standardization of sign language technologies.} } @inproceedings{gren:26013:sign-lang:lrec, author = {Gren, Gustaf and Riemer Kankkonen, Nikolaus}, title = {A Pose-Based Pipeline for Annotation of Headshakes in Sign Language Corpora}, pages = {193--202}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26013.html}, doi = {10.63317/4g5mwahb527o}, abstract = {This paper introduces a pose-based pipeline designed to support scalable annotation of headshakes in sign language corpora. Motivated by the scarcity of annotated datasets and the need for quantitative typological research, the study evaluates whether automated detection can reduce human annotation effort. The system operates on yaw trajectories extracted with MediaPipe Holistic and uses sliding-window segmentation with neural sequence models (LSTM/CNN) to surface candidate segments for review. Training and evaluation are conducted on a subset of the German Sign Language (DGS) Corpus annotated to target grammatical headshakes functioning as negation rather than for every instance of headshakes. On the DGS dataset the best performing LSTM model achieves an F2-score of 0.45, recall of 0.63. Despite the narrow annotation scope, the pipeline reduces search space: annotators need review only 13{\%} of frames to recover 87{\%} of labeled instances. Error analysis indicates that many false positives correspond to plausible head movements excluded by the annotation criteria. A pilot transfer to Swedish Sign Language shows reduced effectiveness without adaptation, underscoring the need for alignment in cross-lingual transfer scenarios.} } @inproceedings{halbout:26028:sign-lang:lrec, author = {Halbout, Julie and Braffort, Annelies and Gouiff{\`e}s, Mich{\`e}le and Fabre, Diandra and Lascar, Julie}, title = {Learning to Spot Signs from Named Entities. A study on {French} {Sign} {Language}}, pages = {203--211}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26028.html}, doi = {10.63317/26i8n4zuyzyx}, abstract = {French Sign Language (LSF) is a low-resourced language, with few available corpora, most of which being only partially annotated. Previous work on other sign languages has explored automatic sign annotation using subtitles as weak supervision, existing signaries, or mouthing cues. This paper focuses on the corpus Matignon-LSF, by first leveraging lexical token spotting then by studying Named Entities (locations, companies, persons). Accounting for the Named entities enables the automatic detection of 30\{\%} to 100\{\%} more signs per class and improves the spotting of rare signs. In addition, this work provides insights into the signing of named entities and contributes resources for improving LSF-to-French translation models.} } @inproceedings{imashev:26040:sign-lang:lrec, author = {Imashev, Alfarabi and Alizadeh, Tohid}, title = {The Iterative Development and Evaluation Framework for {Kazakh-Russian} Signing Avatars Targeted to Native Deaf Signers}, pages = {212--225}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26040.html}, doi = {10.63317/234kquyfezqr}, abstract = {Nowadays, existing research predominantly focuses on already well-researched sign languages. However, the most extensive studies of sign language in Kazakhstan, which adhere to international standards, started about a decade ago. Native deaf signers in Kazakhstan can often suffer from insufficient educational opportunities, which may result in limited reading proficiency too. Sometimes, deaf signers can recognize letters and read words, but they may not fully understand the overall concept and need to break it down into a sequence of simpler ideas to comprehend it better. Consequently, signing avatars have the potential to interpret internet statements, movie subtitles, or YouTube videos, and this sign language production may increase accessibility and improve communication between deaf and hearing individuals, as well as between humans and avatars. An equally critical challenge is how to develop a tool that will help deaf signers evaluate the performance, appearance, and naturalness of signing avatars without relying on written text across all sign languages, particularly in underserved communities. This paper outlines the iterative development of the Kazakh-Russian Sign Language interpreting avatar, ongoing improvements to the evaluation instrument, and a comparative analysis of this instrument with another evaluation method designed to attain the same objective.} } @inproceedings{inan:26015:sign-lang:lrec, author = {Inan, Mert and Imai, Saki and Marshall, Anna and Karel, Tessa and Alikhani, Malihe}, title = {Movement Coherence in High Visual Load Environments: Implications for Attention in Mixed-Hearing Classes}, pages = {226--238}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26015.html}, doi = {10.63317/4itezpkm8f7r}, abstract = {Signed interpretation in movement based instruction creates high visual load environments in which spoken language, sign language, and physical demonstration compete for the same perceptual channel. We present a participatory multimodal observational study of mixed hearing movement and mindfulness classes in which Deaf, Hard of Hearing, and hearing participants practice together. Based on synchronized video recordings and instructor interviews, we examine how alignment across demonstration, signed instruction, and bodily execution is achieved and restored in real time. Drawing on theories of grounding, repair, and sign language interaction, we conceptualize movement coherence as alignment across these parallel streams and describe how breakdowns trigger observable attention shifts and distributed repair across participants, interpreters, and instructors. Across sessions, we identify recurrent coordination strategies including peer checking, freeze and scan, interpreter repositioning, tactile cueing, and pacing adjustment. Our findings provide an empirically grounded account of grounding under attentional constraint in inclusive embodied settings, with implications for sign language interpretation, multimodal discourse, and the design of accessible movement instruction. This paper includes deidentified materials derived from recorded sessions, including selected keyframes, structured interactional annotations, and anonymized instructor and participant survey responses.} } @inproceedings{khan:26047:sign-lang:lrec, author = {Khan, Sarmad and McLoughlin, Simon D. and Murtagh, Irene}, title = {A Comparative Analysis of Traditional and Contemporary Visual Features for Computational Annotation of {Irish} {Sign} {Language}}, pages = {239--247}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26047.html}, doi = {10.63317/4kar89jtkdy5}, abstract = {Automatic annotation of sign language data is critical for advancing linguistic research and developing sign language technologies, yet it remains a major bottleneck due to the inherently motion-based and multi-modal nature of signing. Irish Sign Language, like many sign languages, presents challenges for computational annotation and sign language processing due to limited annotated corpora and the inherent difficulty of reliably annotating movement, trajectories, and coarticulation across manual and non-manual articulators. This paper presents an automated computational framework for gloss-level annotation support in Irish Sign Language, designed to assist scalable corpus annotation by learning motion-related cues directly from sign language videos. Using ELAN-aligned segments from the Signs of Ireland Corpus, we compare contemporary self-supervised visual representations with traditional pose-based features derived from explicit skeletal tracking, evaluating three feature configurations: DINOv2, MediaPipe, and multi-modal fusion. Our results show that self-supervised visual embeddings achieve the highest average accuracy 86.12{\%}, outperforming both multi-modal fusion 84.28{\%} and pose-based representations 76.74{\%}. This indicates that recent visual models can implicitly encode linguistically relevant motion information, including articulator movement and transitional dynamics, reducing the need for explicit landmark extraction in practical annotation pipelines. Overall, this work provides empirical guidance and a deployable computational framework to support computational annotation and enrichment of sign language corpora.} } @inproceedings{khristoforova:26050:sign-lang:lrec, author = {Khristoforova, Evgeniia and Poryadin, Roman}, title = {{HeSLEx}: A novel online questionnaire for heritage sign language research}, pages = {248--255}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26050.html}, doi = {10.63317/586e6zxs948g}, abstract = {In this paper, we present Heritage Sign Language Experience (HeSLEx), a novel online sociolinguistic questionnaire adapted from the heritage spoken language survey HeLEx (Tomi{\'c} et al., 2023) to provide a standardized community profile prior to data collection. Heritage sign languages are minority sign languages used by Deaf signers in migration contexts and thus offer a unique window on bilingualism in the visual modality. HeSLEx is designed to be visual-first: most content is delivered as videos featuring signing in Russian Sign Language (RSL) by community member in a JavaScript/jsPsych interface. To accommodate heterogeneous RSL comprehension, each video includes optional Russian and German text hidden behind a "Show text" button. HeSLEx adds sign-specific modules, including participant and parental hearing status; modality-appropriate proficiency ratings (signing/comprehension for RSL and German Sign Language; reading/writing for Russian and German); educational histories and language(s) of instruction; interactional contexts central to Deaf life (including Deaf clubs); and Deaf-centered identity and language-attitude measures. Many items use slider scales to yield continuous predictors. The tool is designed to be adaptable to other sign language pairs in the framework of heritage language research and beyond.} } @inproceedings{klezovich:26051:sign-lang:lrec, author = {Klezovich, Anna and Mesch, Johanna and Henter, Gustav Eje and Beskow, Jonas}, title = {Comparison of Low Bitrate Quantizers for Encoding {Swedish} {Sign} {Language}}, pages = {256--261}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26051.html}, doi = {10.63317/54ffsuydifyk}, abstract = {This paper investigates the bitrate--distortion trade-off of different discrete representations for Swedish Sign Language (STS) using the STS Mocap v1 motion capture dataset. We compare the K-Means algorithm with the Residual Vector Quantized Variational Autoencoder (RQ-VAE) to determine how efficiently each method preserves salient motion information at low bitrates. The results show that RQ-VAE consistently achieves lower reconstruction error than K-Means at matching bitrates, particularly for body motion, and better preserves the signing space volume. We further demonstrate that quantized representations can serve as conditioning for a flow-matching generative model, producing plausible but still imperfect sign sequences at low bitrates. These findings highlight the advantages of vector quantized models for efficient sign language motion encoding.} } @inproceedings{kopf:26030:sign-lang:lrec, author = {Kopf, Maria and Konrad, Reiner and Langer, Gabriele and Schulder, Marc and K{\"o}nig, Lutz}, title = {Exploring Aspects of Spontaneous Signing in the {DGS} {Corpus}}, pages = {262--274}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26030.html}, doi = {10.63317/5bd5xeb3kh7u}, abstract = {Most use of sign language is spontaneous, unplanned, embedded in a one-to-one situation and transient. General sign language corpora aim at such naturalistic data. Thus it can be expected that they include phenomena of spontaneous language similar to the ones described for spontaneous speech in vocal languages: that is, (dis)fluencies such as pauses, hesitations, errors, false starts and repairs as well as discourse markers. In this paper we explore which of the known phenomena of spontaneous language from previous research on vocal and sign languages could be identified in the DGS Corpus using the annotations at hand. We describe our search strategies, consider additional annotation tiers for spontaneous language, and provide examples for the phenomena identified.} } @inproceedings{lepp:26032:sign-lang:lrec, author = {Lepp, Lisa and De Sisto, Mirella and Shterionov, Dimitar}, title = {Two-Handed Signs and Handedness: Phonological Implications for Sign Language Structure}, pages = {275--286}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26032.html}, doi = {10.63317/3per9mf2462d}, abstract = {Handedness ---the use of one versus two hands in sign production--- has traditionally been discussed in relation to dominance and symmetry conditions, yet it remains underrepresented in formal phonological models of sign languages. This paper argues that handedness constitutes a core phonological parameter that directly influences the structure and interaction of movement, handshape, location, and orientation. Building on hierarchical and dependency-based approaches, we propose an adapted phonological dependency model that explicitly integrates handedness in the representation of manual articulators. In one-handed signs, features are specified for a single active hand. In two-handed signs, feature distribution is constrained by symmetry and dominance conditions, which regulate whether the hands must share features or may differ in a structurally restricted way. This structural encoding accounts for variation phenomena such as weak add, weak prop, and weak drop as constrained adjustments within the phonological system. From a technical perspective, this refinement suggests more formal restrictiveness and empirical discriminability within the feature geometries, reduced representational ambiguity, and improved empirical testability across theoretical, corpus-based, and computational implementations, strengthening the interface between phonological theory and sign language technology.} } @inproceedings{loy:26043:sign-lang:lrec, author = {Loy, Lisa and Morgan, Hope E.}, title = {{HNS2CF}: A Mapping Tool from {HamNoSys} to {SL} {CatForm}}, pages = {287--296}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26043.html}, doi = {10.63317/3m5m8sp4qe6j}, abstract = {Over the past six decades, a variety of systems have been developed for representing sign language forms, from Stokoe Notation (Stokoe, 1960) to SignWriting (Sutton, 1999) and lexical database schemas. Each was designed with specific goals and applications, leading to a fragmented landscape of representations. To enable greater interoperability and data sharing among sign language users and researchers, we propose a robust approach to translating between notation systems. As a first step in this direction, we introduce a formal mapping framework between HamNoSys and the SL CatForm coding schema, describe its implementation, and present empirical evidence of its performance. An extensive evaluation of mapping mismatches revealed improvements to the mapping logic needed to further advance the HNS2CF mapping tool. However, the initial version of the system already achieves an overall accuracy of 76.7{\%} and an in-depth analysis reveals that many apparent mismatches stem from annotator disagreement rather than mapping errors, indicating that the tool's actual accuracy is even higher. These results demonstrate the feasibility and promise of establishing mapping mechanisms across sign representation systems.} } @inproceedings{lunajimenez:26008:sign-lang:lrec, author = {Luna-Jim{\'e}nez, Cristina and Eing, Lennart and Esteban Romero, Sergio and Schneeberger, Tanja and Gebhard, Patrick and Nunnari, Fabrizio and Andr{\'e}, Elisabeth}, title = {Emotion Recognition in {German} {Sign} {Language} with Facial Action Units}, pages = {297--305}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26008.html}, doi = {10.63317/37cwjrcccu7p}, abstract = {Emotion Recognition research in Sign Languages is still in its infancy. Still today, there exists a lack of knowledge about appropriate annotation guidelines and the impact that facial expressions, body postures and head positions have in recognizing emotions while signing, considering that sign language encompasses manual and non-manual cues with linguistic purposes. In this article, we present an acquisition protocol to record acted emotions in German Sign Language under four scenarios (High-Valence and High-Arousal, High-Valence and Low Arousal, Low-Valence and High-Arousal, and Low-Valence and Low-Arousal). The goal is to provide a reference dataset to explore the use of machine learning techniques for an automated classification of emotions in sign language utterances. As a baseline reference, we trained static models with features extracted from the facial muscle activations. The best model achieved an accuracy of 68.84{\%} and a F1 of 67.96{\%} with a random forest trained on the statistics extracted from Action Units. These results highlight the importance of facial expression in sign language, not only for carrying linguistic information but also for transmitting emotions. Results also indicate challenges in detecting emotions in the High-Valence and Low Arousal scenario, which suggests future investigation lines to explore.} } @inproceedings{lunajimenez:26011:sign-lang:lrec, author = {Luna-Jim{\'e}nez, Cristina and Eing, Lennart and Withanage Don, Daksitha and Gonz{\'a}lez, Marco and Nunnari, Fabrizio and Perniss, Pamela and Gebhard, Patrick and Andr{\'e}, Elisabeth}, title = {{DGS-BIGEKO}: A Dataset for Hypothetical Emergency Scenarios in {German} {Sign} {Language}}, pages = {306--314}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26011.html}, doi = {10.63317/2kkcv47dtm53}, abstract = {In this article, we describe DGS-BIGEKO, a sign language dataset containing a conversation in a crisis scenario signed by a professional interpreter in German Sign Language (DGS). The dataset comprises 14 sentences with common questions and answers from protocols occurring in emergency call scenarios translated into DGS. Additionally, the dataset contains signs for an additional 108 concepts that are relevant to emergency call scenarios. The dataset is intended to support research in sign language linguistics and sign language machine translation by providing resources in a very specific domain, where no previous resources are available in DGS. The dataset is freely available for research purposes at the following address: https://doi.org/10.5281/zenodo.18458557} } @inproceedings{maina:26067:sign-lang:lrec, author = {Maina, Ezekiel and Wanzare, Lilian and Obuhuma, James}, title = {Perceptual Validation of {3D} Pose, Guided Sign Language Synthesis}, pages = {315--323}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26067.html}, doi = {10.63317/29qyih7xu7ym}, abstract = {Sign language corpora face a structural tension between open-access requirements and the irreducible biometric identity embedded in visual, gestural data. While 3D pose estimation enables signer-agnostic abstraction, the representational adequacy of pose-based modeling for preserving linguistic structure remains underexplored. This paper introduces a perceptually-grounded kinematic modeling framework that formalizes 3D landmark sequences as an intermediate linguistic representation and validates their adequacy through avatar-mediated synthesis and large-scale human evaluation. Using 30370 gloss-level Kenyan Sign Language (KSL) segments derived from the AI4KSL corpus, we construct normalized 3D motion trajectories via MediaPipe Holistic. These trajectories are retargeted to parameterized avatars through a constrained kinematic mapping that preserves non-manual marker geometry and articulatory timing. We define a dual evaluation paradigm combining geometric fidelity metrics (PCK=92.7{\%}, OKS=0.88, PCP=91.5{\%}, PDJ>85.3{\%}) with perceptual constructs measured across a statistically powered Deaf participant cohort (N=384). Results demonstrate a strong predictive relationship between structural joint precision and perceived gesture clarity (r=0.76, p<.01), suggesting that linguistic adequacy is partially recoverable from normalized kinematic structure. Furthermore, representational diversity in avatar instantiation significantly increases perceived inclusivity without degrading intelligibility. These findings establish pose-based motion abstraction not merely as an anonymization technique but as a viable corpus-level modeling layer for ethically sustainable language in motion.} } @inproceedings{malaia:26027:sign-lang:lrec, author = {Malaia, Evie A. and Krebs, Julia and Harbour, Eric and Martetschl{\"a}ger, Julia and Schwameder, Hermann and Roehm, Dietmar and Wilbur, Ronnie B.}, title = {The Displacement-Velocity Dissociation in Sign Language Learning: Kinematic Signatures of Event Structure in Novice {{\"O}GS} Signers}, pages = {324--332}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26027.html}, doi = {10.63317/2r4douivdpjm}, abstract = {This study investigates how adult learners acquire linguistically contrastive movement patterns in Austrian Sign Language ({\"O}GS), focusing on the telic/atelic distinction predicted by the Event Visibility Hypothesis. Telic verbs (bounded events) are produced by proficient Deaf signers with shorter duration and temporally precise, low-entropy velocity profiles, whereas atelic verbs (unbounded processes) show more continuous motion. Using 3D motion capture (300 Hz), we compared 8 novice learners (6--12 weeks of instruction) with 6 proficient Deaf signers across 71 verbs. Linear mixed-effects models revealed a dissociation between gross movement patterning and fine-grained velocity profile structure in learner productions. Learners correctly reproduced the proportional path-length contrast between telic and atelic verbs, replicating the gross spatial distinction of proficient signers. However, temporal marking of the telic/atelic contrast was underproduced: learners showed a significantly smaller duration difference between verb types than proficient signers, while total path length did not differ significantly between verb types or groups. Temporal control showed significant between-group differences: learners exhibited elevated sample entropy, with non-proficient velocity profiles within individual sign productions, though spatial consistency across trials (STI) was comparable to that of proficient signers. Peak velocity did not differ between groups, suggesting that learners can reach target speeds but cannot yet modulate temporal structure reliably. These findings support distinct learning trajectories for gross movement patterning and fine-grained motion complexity, and demonstrate that velocity profile structure within signs constitutes a core linguistic target in sign language learning.} } @inproceedings{marrocu:26025:sign-lang:lrec, author = {Marrocu, Maria Grazia}, title = {{CEFR}-Based Assessment in Sign Languages: The Case of {LSE} and Perspectives for {LIS}}, pages = {333--340}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26025.html}, doi = {10.63317/5pdt9ru4fqfc}, abstract = {This study examines the application of the Common European Framework of Reference for Languages (CEFR) to Spanish Sign Language (LSE) in a university context, with reference to the Italian situation (Council of Europe, 2020). In Spain, CEFR descriptors are already integrated into academic programmes for the assessment of LSE, whereas in Italy the context remains uneven due to the lack of shared criteria for the teaching and assessment of Italian Sign Language (LIS). The research project, conducted jointly by Ca' Foscari University of Venice and Rey Juan Carlos University of Madrid, adopts a longitudinal and comparative design focusing on the first three CEFR proficiency levels (A1, A2, B1) of LSE among L2M2 learners (second language second modality). A mixed-methods approach combining classroom observations, self-assessment instruments, and standardised assessment rubrics is used to analyse the alignment between students' self-assessments and instructors' external evaluations, with particular attention to linguistic and metacognitive awareness. The findings show increasing accuracy in self-assessment as proficiency develops, alongside recurring issues such as the overestimation of receptive skills and the underestimation of productive competence. These results highlight the need for targeted assessment interventions and contribute to the development of CEFR-consistent evaluation practices for sign languages.} } @inproceedings{morgan:26042:sign-lang:lrec, author = {Morgan, Hope E. and Isard, Amy and Dang, Anh}, title = {Improving phonological distance measures for signs: the {CatFormCompare} tool}, pages = {341--350}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26042.html}, doi = {10.63317/3etemouixntr}, abstract = {This paper describes the CatFormCompare tool, designed to enable the comparison of phonological content between pairs of signs, especially in larger datasets. With this tool and a schema for coding categorical form (the SL CatForm coding schema), a pipeline is created that allows a feedback mechanism for advancing research---specifically by directly addressing one of the hard problems in sign language phonology: how to extract true minimal pairs from datasets coded for categorical form? Solving this problem would simultaneously improve phonological distance measurements for sign languages because it would mean that the units for measuring distance are grounded in the linguistic structure of the language and not simply a by-product of the coding system. Here we report on the tool and the first evaluation of its functioning.} } @inproceedings{mostowski:26053:sign-lang:lrec, author = {Mostowski, Piotr and Kuder, Anna and W{\'o}jcicka, Joanna}, title = {Assisting Corpus Annotation: Automatic {BIO}-Tagging of Clause-Like Units in {Polish} {Sign} {Language}. A Pilot Study on Corpus Data}, pages = {351--360}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26053.html}, doi = {10.63317/364zmis7ppgo}, abstract = {The creation of large-scale sign language corpora is often bottlenecked by the labour-intensive process of multi-layered annotation that requires manual analysis. One of the annotation steps is the challenging and time-consuming task of segmenting continuous signing into clause-like-units (CLUs). In this paper, we propose an automated segmentation framework for Polish Sign Language (PJM) designed to support manual annotation. To detect sentence boundaries, we adapt the Multi-Stage Temporal Convolutional Network (MS-TCN) architecture, enhanced with a Channel Attention mechanism, to effectively fuse multimodal skeleton features (hands, body, and face) extracted via MediaPipe. We evaluate the model on a diverse subset of the PJM Corpus (40 video files, 25 signers), containing nearly 16,000 manually annotated clauses prior to the start of this study. The proposed method achieves a Segmental F1-score of 75.43{\%} at IoU = 0.10 and 57.52{\%} at IoU = 0.50, demonstrating a strong capability in localising sentence boundaries. Furthermore, ablation studies reveal that fusing manual kinematics with non-manual prosodic cues (face) yields a significant performance gain (+13.6 pp) over unimodal baselines, empirically confirming the linguistic necessity of incorporating both manual and non-manual articulators in the process of sentence delimitation. The solution offers a viable means for reducing CLU annotation time by automatically generating high-quality clause boundary proposals.} } @inproceedings{murtagh:26031:sign-lang:lrec, author = {Murtagh, Irene and Schulder, Marc and Herrmann, Annika and Paulus, Liona and Bleicken, Julian and Blekos, Kostas and Konstantakopoulos, Athanasios and Antzakas, Klimis and Kosmopoulos, Dimitrios and Valls, Eva and Marques, Ricardo and Blat, Josep and Karampidis, Konstantinos and Elsendoorn, Ben}, title = {Introducing {VISTA-SL}: A Multilingual e-Learning Platform for Deaf and Hearing Learners of Sign Languages}, pages = {361--370}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26031.html}, doi = {10.63317/5dk2bc2vn43t}, abstract = {This article introduces the VISTA-SL project, which aims to create an integrated e-learning platform for four European sign languages: German Sign Language, Greek Sign Language, Irish Sign Language, and Dutch Sign Language. Designed as a complement to face-to-face classes, the VISTA-SL platform will combine expertise in sign language education and education technologies to provide an adaptive and interactive learning environment suitable for deaf, hard of hearing and hearing users seeking to learn a sign language, whether it constitutes their first language or not. Building on a co-ordinated curriculum that covers vocabulary, grammar and Deaf culture materials, the platform will provide video material presented by deaf L1 signers, together with games and gamification features to motivate learning, while also providing several assistive technologies. By leveraging cutting edge language processing and computer vision approaches, the platform will provide augmented reality feedback, 3D avatars and an LLM-based virtual instructor, as part of the learning environment. VISTA-SL is developed in collaboration with end-user focus groups, comprising deaf, hard of hearing and hearing individuals. This will serve to ensure that the educational platform aligns with the expectations and needs of its intended users.} } @inproceedings{obrien:26035:sign-lang:lrec, author = {O'Brien, Catherine and Sant, Gerard and M{\"u}ller, Mathias and Ebling, Sarah}, title = {Evaluation of Pose Estimation Systems for Sign Language Translation}, pages = {371--386}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26035.html}, doi = {10.63317/4shxzirxykmm}, abstract = {Many sign language translation (SLT) systems operate on pose sequences instead of raw video to reduce input dimensionality, improve portability, and partially anonymize signers. The choice of pose estimator is often treated as an implementation detail, with systems defaulting to widely available tools such as MediaPipe Holistic or OpenPose. We present a systematic comparison of pose estimators for pose-based SLT, covering widely used baselines (MediaPipe Holistic, OpenPose) and newer whole-body/high-capacity models (MMPose WholeBody, OpenPifPaf, AlphaPose, SDPose, Sapiens, SMPLest-X). We quantify downstream impact by training a controlled SLT pipeline on RWTH-PHOENIX-Weather 2014 where only the pose representation varies, evaluating with BLEU and BLEURT. To contextualize translation outcomes, we analyze temporal stability, missing hand keypoints, and robustness to occlusion using higher-resolution videos from the Signsuisse dataset. SDPose and Sapiens achieve the best translation performance (BLEU ~11.5), outperforming the common MediaPipe baseline (BLEU ~10). In occlusion cases, Sapiens is correct in all tested instances (15/15), while OpenPifPaf fails in nearly all (1/15) and also yields the weakest translation scores. Estimators that frequently leave out hand keypoints are associated with lower BLEU/BLEURT. We release code that can be used not only to reproduce our experiments, but also considerably lowers the barrier for other researchers to use alternative pose estimators.} } @inproceedings{okrouhlikova:26017:sign-lang:lrec, author = {Okrouhl{\'i}kov{\'a}, Lenka}, title = {Designing a Data Model for a Diachronic Sign Language Database: A Case Study of Nineteenth-Century {Bohemian} Sources}, pages = {387--397}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26017.html}, doi = {10.63317/5hxyoxmdi8ri}, abstract = {Diachronic research on sign languages is limited by the fragmentary and heterogeneous nature of historical documentation. Eighteenth- and nineteenth-century printed texts and manuscripts contain valuable lexical data, but their descriptions vary in precision, terminology, and representational conventions. This paper proposes a structured data model for a diachronic sign language database designed to systematise such archival materials. The proposed model adopts a multi-layered architecture that separates primary evidence from analytical interpretation, distinguishes attested from inferred sign parameters, applies graded confidence levels, and encodes structural, iconic, and metaphorical properties in parallel layers. Detailed source metadata ensures traceability and explicit representation of uncertainty. The model is illustrated through sign attestations drawn from nineteenth century Bohemian sources. The case study demonstrates that even fragmentary records, most commonly documented in dictionaries and pedagogical materials through written descriptions or illustrations, can be systematically represented within a unified data model suitable for structured comparison and diachronic analysis. The proposed model may also provide a methodological basis for comparable work on other European sign languages.} } @inproceedings{orazumbekov:26060:sign-lang:lrec, author = {Orazumbekov, Batyrbek and Bayanov, Daniyal and Kaltay, Aruzhan and Sandygulova, Anara}, title = {A Video-Based Reverse Dictionary for Sign Language Using Gesture Similarity}, pages = {398--407}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26060.html}, doi = {10.63317/54ysrywg3ktr}, abstract = {Sign language recognition systems are usually modeled as classification systems that map gesture videos to pre-defined glosses. But these systems do not allow similarity searches, where a user can search for similar gestures without knowing the corresponding gloss. This paper presents a pose-based video-to-video search framework for isolated signs, which acts as a reverse gesture dictionary. The system employs keypoints on the skeletal structure instead of RGB images. Two architectures are proposed for modeling temporal information: an encoder with self-attention in a Transformer architecture and a Spatial-Temporal Graph Convolutional Network (ST-GCN). The embedding space is optimized using metric learning objectives, including supervised contrastive learning and ArcFace angular margin loss. The performance of the retrieval system is evaluated on the WLASL dataset using ranking metrics like Recall@K and mean Average Precision (mAP). Experiments reveal that the temporal modeling using the Transformer architecture is an improvement over the graph-based modeling approach in the low-shot learning scenario. The attention-based temporal pooling approach further enhances the ranking quality, with the best-performing model achieving an mAP of 0.237 on the WLASL validation set. Cross-dataset evaluation on a 226-label AUTSL dataset reveals non-trivial generalization performance on the unseen dataset, despite training only on the WLASL dataset.} } @inproceedings{othamar:26059:sign-lang:lrec, author = {Othamar, Elisabeth and Scherrer, Yves}, title = {{Norwegian} {Sign} {Language}: Overview of Resources and Experiments with Automatic {SignWriting} Transcription}, pages = {408--418}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26059.html}, doi = {10.63317/3unezo3kea9w}, abstract = {Norwegian Sign Language (NTS) remains an under-resourced sign language despite its official recognition in Norway since 2022. The limited availability of structured, reusable, and publicly accessible datasets continues to hinder both linguistic research and the development of sign language technologies such as recognition and translation systems. This paper presents an overview of existing datasets and potential data sources for NTS, categorizing them by accessibility, format, and suitability for computational research. We further discuss legal, ethical, and practical considerations related to data reuse, including copyright and privacy constraints. In addition, we report on a series of pilot experiments exploring alternative data acquisition strategies, including dictionary videos, SignWriting resources, and broadcast news material. These preliminary experiments explore whether automatic SignWriting transcription can serve as an intermediate representation for NTS, and examine its potential role in sign identification within continuous signing. The aim of this work is both to document ongoing efforts and to support future initiatives toward the sustainable development of NTS resources.} } @inproceedings{poitier:26022:sign-lang:lrec, author = {Poitier, Pierre and Fink, J{\'e}r{\^o}me and Basso Madjoukeng, Ariel and Couplet, Ad{\'e}la{\"i}de and Leleu, Margaux and Fr{\'e}nay, Beno{\^i}t}, title = {Long-Term Sign Language Data Crowdsourcing Through Collaborative Lexicons}, pages = {419--428}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26022.html}, doi = {10.63317/3t8tpmhi2om8}, abstract = {While there exists a multitude of different sign languages (SLs) across the world, Deaf communities often lack the digital tools required to document and process their languages. In this work, we introduce Mot-Signe (MOSI), an application designed in close collaboration with actors from the French Belgian Deaf community. Our tool enables users to search for French Belgian Sign Language (LSFB) translations or to propose new ones by recording signs themselves. This crowdsourcing approach facilitates the collection of SL data in the wild, enriching the available documentation on LSFB and proposing an innovative response to the data scarcity issue inherent to sign language processing. To evaluate the sustainability of this community-driven data collection, a longitudinal user study was conducted. Following its public release, MOSI demonstrated significant real-world adoption, enabling the collection of over 3,000 distinct LSFB signs. Notably, MOSI captures highly valuable linguistic variations and specialized vocabulary often absent from traditional corpora.} } @inproceedings{renner:26009:sign-lang:lrec, author = {Renner, Fabian and Withanage Don, Daksitha and Andr{\'e}, Elisabeth and Luna-Jim{\'e}nez, Cristina}, title = {Effect of Data Augmentation with Multi-View Perspectives of Signers on the {DGS-Fabeln-1} Dataset}, pages = {429--437}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26009.html}, doi = {10.63317/2zrdptjrx3pa}, abstract = {Sign languages constitute the principal form of communication for deaf communities across the globe. Nevertheless, the development of reliable Continuous Sign Language Translation (CSLT) systems is constrained by the lack of sufficient data and models able to handle spatio-temporal information. In this article, we explore the effect of adding multiview perspectives of the signer to the training set as data augmentation using the UniSign framework for the DGS-Fabeln-1 dataset. Our results reveal that increasing dataset size and using multiple camera perspectives significantly improve performance, with the best configurations achieving BLEU-4 scores of 4.20{\%}. These results provide a competitive baseline for the DGS-Fabeln-1 dataset and guidance for further optimizations of CSLT systems.} } @inproceedings{sazonov:26056:sign-lang:lrec, author = {Sazonov, Dmitriy and Gurbuz, Sevgi and Malaia, Evie A.}, title = {Lost in Expression: Diagnosing Systemic Challenges with Non-Manual Generalization in Sign Language Understanding Tasks}, pages = {438--449}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26056.html}, doi = {10.63317/3ofdq6bwkwik}, abstract = {Incorporation of non-manual information is one of the most challenging aspects of Sign Language Understanding (SLU), as these features contribute to the semantic, syntactic, and pragmatic structure of signed communication as a critical feature of compositional meaning at sign, phrase and sentence level. Despite their key linguistic role, non-manuals are often an afterthought in SLU model and dataset design, with many recent models still neglecting to implement non-manual analysis or evaluate how articulators beyond the hands are contributing to the model prediction. In this work, we identify and analyze the challenges relating to recognition of non-manuals and generalization of their linguistic roles encountered by SLU models, offering new explanations for failures to properly model non-manual behavior. We perform a case study on the subtasks of Continuous Sign Language Recognition and Sign Language Translation by applying the Uni-Sign model to Isharah-1000, a Saudi Sign Language dataset. Using controlled partitioning and feature attribution, we further analyze model behavior and failure cases. With this work we hope to set the stage for the creation of diagnostic frameworks for generalization of non-manuals.} } @inproceedings{schiefner:26019:sign-lang:lrec, author = {Schiefner, Annika and Otterspeer, Gom{\`e}r and S{\"u}mer, Beyza and Roelofsen, Floris}, title = {The {SignBeach} Dataset of {Dutch} {Sign} {Language} ({NGT}) signs}, pages = {450--458}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26019.html}, doi = {10.63317/2whuhuqvwuix}, abstract = {This paper presents the SignBeach dataset, including 1401 lexical signs from Dutch Sign Language (NGT). The items in this dataset represent everyday vocabulary appropriate for primary school children and are part of a larger research project, investigating sign learning in a digital environment. Each sign is presented by four deaf signers in a controlled studio environment. For each item, high quality video recordings are available from five synchronised cameras, providing rich multi-view visual input suitable for linguistic analysis and the development of computer vision pipelines. In addition, we provide three types of computational derivatives: keypoint estimates using MediaPipe, handshape estimates using HaMeR, and 3D body reconstructions using SAM 3D Body. Signs are aligned with lexical entries in the NGT Signbank to provide interoperability of the database with other NGT resources. We outline the construction of the dataset and provide information on opportunities for reuse, for example in the context of psycholinguistic studies or in the context of sign language technology. All materials are available for non-commercial reuse under a CC BY-NC 4.0 license.} } @inproceedings{susman:26023:sign-lang:lrec, author = {Susman, Margaux and Miquel Blasco, Carla and Bulla, Jan}, title = {Comparing Computer Vision Instruments for Eye Blink Analysis}, pages = {459--467}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26023.html}, doi = {10.63317/2vzsgmq46vrk}, abstract = {We compared four tools for analyzing blink velocity and amplitude, examining how MediaPipe, OpenFace, InsightFace, and 3DDFA compare in terms of blink analysis. Building on previous findings that different tools yield different results (Kuznetsova and Kimmelman, 2024), we explored their fixed-effect estimates across linguistic versus non-linguistic blinks, within non-linguistic blinks (eye watering blinks versus gaze-direction-change blinks), and within linguistic blinks (prosodic/turn-taking blinks, sign-aligned/list-marking blinks and backchanneling blinks), while controlling for head pose (Pitch, Roll, Yaw). Using mixed-effects linear models on annotated French Sign Language data, we found tool-specific patterns: consistent negative effects for InsightFace and MediaPipe, but positive. effects for 3DDFA. In addition, the influence of head pose varied across models (Pitch is strongly positive in MediaPipe but negative in InsightFace and some 3DDFA models; Roll and Yaw also switch importance across tools). These discrepancies highlight methodological biases that can distort linguistic interpretations.} } @inproceedings{vandendriessche:26012:sign-lang:lrec, author = {Vandendriessche, Toon and De Coster, Mathieu and Dambre, Joni}, title = {Grounding Sign Language Representation Learning in Phonology}, pages = {468--476}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26012.html}, doi = {10.63317/2kyvv756bfmz}, abstract = {Sign language recognition systems are commonly trained using gloss-level supervision, treating signs as holistic lexical units. While effective for classification, such approaches entangle sub-lexical structure and fail to capture the phonological parameters that govern sign formation, limiting interpretability, robustness, and cross-lingual transfer. In this work, we propose a phonologically informed representation learning architecture that explicitly structures the latent space according to linguistic principles. Grounded in the Dependency Model -- a phonological model used to describe Flemish Sign Language (VGT) -- our hierarchical architecture disentangles parameter-specific subspaces for handshape and location and is trained with multi-label phoneme supervision. To evaluate whether phonological information is directly encoded in the geometry of the embedding space, we introduce a non-parametric probing method that measures neighbourhood consistency across increasing scales. We show that conventional gloss-based networks achieve reasonable performance only for very small neighbourhoods, reflecting incidental visual similarity. In contrast, our disentangled representations maintain stable performance for larger neighbourhoods. This behaviour indicates that phonological structure is preserved across broader regions of the space, yielding more coherent and robust embeddings. Together, our results show that explicit phonological supervision -- and crucially, disentangled representation learning -- provides a principled foundation for interpretable and transferable sign language representations. Keywords: Sign Language, Machine Learning} } @inproceedings{vandenitte:26018:sign-lang:lrec, author = {Vandenitte, S{\'e}bastien and Hern{\'a}ndez, Doris and Ker{\"a}nen, Jarkko and Jantunen, Tommi and Puupponen, Anna}, title = {Towards Integrating Pose Estimation with Neuroimaging for the Analysis of Signed Language Video Stimuli}, pages = {477--483}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26018.html}, doi = {10.63317/2q3vp6hdx56b}, abstract = {We present our project revisiting the video stimuli of an EEG study in Finnish Sign Language to ask whether kinematic properties of the videos impacted their processing by study participants. For each stimulus, an average measure of brain responses across participants is computed. To analyse movement properties in the video stimuli, we rely on MediaPipe for pose estimation. We subsequently report on our project to perform an exploratory analysis of the kinematic properties of the videos which may affect their processing. We focus on several landmarks: the signer's right and left wrists, nose, and upper torso. Our goal is to obtain a kinematic profile of each stimulus video using several average kinematic variables: velocity and acceleration for all selected landmarks, distance between the wrists, and surface covered by the triangular area defined by the left hand, the right hand, and the nose. We conclude by discussing the potential benefits and limitations of this methodological approach.} } @inproceedings{wahl:26036:sign-lang:lrec, author = {W{\"a}hl, Sabrina}, title = {{KWIC} view on Constructed Action ({CA}) and its Collocates in {German} {Sign} {Language} ({DGS}) -- Possibilities and Limitations}, pages = {484--490}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26036.html}, doi = {10.63317/57tm3w2rr3ko}, abstract = {Constructed action (CA) is a phenomenon that is used in signed discourse to show the actions of a referent (cf. Cormier et al., 2015; for DGS, cf. Fischer and Kollien, 2010). To achieve this, the signer adopts the role of the referent. Most studies use retellings as their data base (e.g. Herrmann and Pendzich, 2018; Cormier et al., 2015). Consequently, there is less research on CA and its use in data that is not influenced by stimuli. Though there is a considerable number of studies on CA, the phenomenon is still not well understood. One possible way to understand this multifaceted phenomenon better is to analyse collocations in conversations. In spoken language lexicography concordance lines -- also known as keyword in context (KWIC) -- have proven to be a useful tool in the analysis of collocations. The data used in this study are Free conversations in the Public DGS Corpus. This paper explores the possibilities and limitations of concordance lines as a tool to analyse collocational behaviour of CA. It also presents preliminary results regarding CA and its collocates, which may be explored further in the future.} } @inproceedings{wang:26054:sign-lang:lrec, author = {Wang, Zirui and Bono, Mayumi}, title = {Beyond {BLEU}: Linguistic Invisibility and Interactional Repair Sequence in End-to-End Sign Language Translation}, pages = {491--500}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26054.html}, doi = {10.63317/3drmbqqsx7a8}, abstract = {Recent advances in end-to-end sign language translation (SLT) have achieved benchmark performance, yet little is known about whether these systems preserve the multi-channel linguistic structures that are essential for real-world communication. We argue that current optimization and evaluation practices create a form of linguistic invisibility, where interactionally decisive non-manual signals (NMS) are systematically underrepresented despite high translation scores.To empirically examine this issue, we analyze an interactional repair sequence from a Japanese Sign Language (JSL) conversational corpus as a diagnostic probe. Combining qualitative interactional analysis with kinematic measurements, we demonstrate a consistent manual--mouth decoupling pattern in which semantic resolution is carried primarily by mouthing while manual articulation remains largely constant. We show that such cross-channel contrast is unlikely to be preserved under current end-to-end training objectives that prioritize global motion similarity. Based on these findings, we argue that progress in SLT should be evaluated not only by sequence-level accuracy but also by the preservation of linguistically contrastive structures, motivating the development of diagnostic, multi-channel evaluation protocols for future SLT benchmarks. We therefore propose incorporating multi-channel diagnostic evaluation sets and decoupling-sensitive metrics into future SLT benchmarking frameworks, providing a pathway toward models that achieve both high performance and linguistic structural visibility.} } @inproceedings{zhao:26014:sign-lang:lrec, author = {Zhao, Mingyu and Yang, Zhanfu and Zhou, Yang and Xia, Zhaoyang and Jin, Can and He, Xiaoxiao and Lin, Shuhang and Neidle, Carol and Metaxas, Dimitris}, title = {Continuous Sign Language Recognition using Multimodal Input and Handshape-aware Boundary Detection}, pages = {501--512}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion}, maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {16}, month = may, year = {2026}, isbn = {978-2-493814-82-1}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26014.html}, doi = {10.63317/22bkv35eirvm}, abstract = {This paper employs a multimodal approach for continuous sign recognition by first using ML for detecting the start and end frames of signs in videos of American Sign Language (ASL) sentences, and then by recognizing the segmented signs. For improved robustness, we use 3D skeletal features extracted from sign language videos to take into account the convergence of sign properties and their dynamics that tend to cluster at sign boundaries. Another focus of this paper is the incorporation of information from 3D hand configuration for boundary detection. To detect handshapes normally expected at the beginning and end of signs, we pretrain a handshape classifier for detection of 87 linguistically defined canonical handshape categories using a dataset that we created by integrating and normalizing several existing datasets. A multimodal fusion module is then used to unify the pretrained sign video segmentation framework and handshape classification models. Finally, the estimated boundaries are used for sign recognition, where the recognition model is trained on a large database containing both citation-form isolated signs and signs pre-segmented (based on manual annotations) from continuous signing---as such signs often differ a bit in certain respects. We evaluate our method on the ASLLRP corpus and demonstrate significant improvements over previous work.} } @proceedings{lrec:sign-lang:24, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, title = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, url = {https://aclanthology.org/2024.signlang-1.pdf}, doi = {10.63317/4e7aayu2htd6} } @inproceedings{battisti:24019:sign-lang:lrec, author = {Battisti, Alessia and Tissi, Katja and Sidler-Miserez, Sandra and Ebling, Sarah}, title = {Advancing Annotation for Continuous Data in {Swiss} {German} {Sign} {Language}}, pages = {1--12}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24019.html}, doi = {10.63317/39wbj3gkak4d}, abstract = {This paper presents a transcription and annotation scheme introduced specifically for L1 and L2 continuous data of Swiss German Sign Language, with potential applicability to other sign languages. The scheme includes a novel way of annotating linguistic errors in L2 data, thereby contributing to a deeper understanding of sign language learning. An initial validation approach is outlined, revealing challenges and underscoring the necessity for a more comprehensive method for validating sign language (learner) data. The paper emphasizes the overarching goal of achieving interoperability among sign language corpora and research groups, particularly in advancing sign language data validation techniques.} } @inproceedings{battisti:24025:sign-lang:lrec, author = {Battisti, Alessia and van den Bold, Emma and G{\"o}hring, Anne and Holzknecht, Franz and Ebling, Sarah}, title = {Person Identification from Pose Estimates in Sign Language}, pages = {13--25}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24025.html}, doi = {10.63317/4xuiacemwayt}, abstract = {Sign language recognition models require extensive training data. Effectively anonymizing such data remains a complex endeavor due to the crucial role of facial features. While pose estimation techniques have traditionally been considered a means of yielding anonymized data, the findings reported in this paper challenge this assumption: We conducted a study involving Swiss German Sign Language (DSGS) users, presenting them with pose estimates from DSGS video samples. The participants' task was to identify the signers' language levels and identities from skeletal representations. Our findings reveal that the extent to which sign language users were capable of recognizing familiar signers depended on their language level, with deaf experts achieving the highest accuracy. We demonstrate that an automatic classifier obtains comparable results in multi-label language level recognition (F1=0.64) and person identification (F1=0.31). This emphasizes the need to reconsider the fundamentals of video anonymization towards guaranteeing sign language users' privacy.} } @inproceedings{bono:24013:sign-lang:lrec, author = {Bono, Mayumi and Okada, Tomohiro and Skobov, Victor and Adam, Robert}, title = {Data Integration, Annotation, and Transcription Methods for Sign Language Dialogue with Latency in Videoconferencing}, pages = {26--35}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24013.html}, doi = {10.63317/2mxwrf8r2ax8}, abstract = {Since the start of the coronavirus disease 2019 (COVID-19) pandemic, online conferencing has become a part of daily life for many people. This lifestyle change applies to hearing people and Deaf people. How have Deaf individuals, who essentially communicate in three-dimensional space, experienced this shift? To address this question, the present study recorded online conversations between Deaf people using the videoconferencing tool Zoom. In this article, we explain how latency is captured in videoconferencing dialogue and how recorded data are integrated and annotated using an annotation tool (ELAN). First, we present two examples of the analysis to clarify basic theoretical issues that affect turn-taking via videoconferencing systems focusing on the sequence structure of `greetings' and `encounters.' Videoconferencing dialogues often begin with the participants greeting each other, which may be delayed because of the nature of online communication or the technical specifications of each individual's device. Next, to discuss sequential issues with videoconferencing dialogue, we introduce how the fundamental adjacency pair, such as question (first pair part: FPP) and answer (second pair part: SPP), appears to each participant on their computers with latency. This research shows that recording videoconferencing dialogues with latency is useful for next-generation data collection in vision-sensitive sign languages, as well as audio-centred spoken languages with gestures.} } @inproceedings{borstell:24003:sign-lang:lrec, author = {B{\"o}rstell, Carl}, title = {Evaluating the Alignment of Utterances in the {Swedish} {Sign} {Language} Corpus}, pages = {36--45}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24003.html}, doi = {10.63317/2gytjus3cotq}, abstract = {The Swedish Sign Language (STS) Corpus mainly contains segmentations on the lexical level (i.e. signs), which makes it difficult to extract information at clause- or utterance-like levels. In this paper, I evaluate three different methods of segmenting the data into larger units: prosodic, syntactic and translation-based utterance units. The results show that none of the utterance units have particularly high accuracy in their alignment with the others, illustrating the challenges facing researchers who are looking to extract meaningful units above the lexical level. In a second step, I extract articulation information from the corpus videos using computer vision methods, but find no clear alignment of articulatory features of the hands and head with the boundaries of the utterance units.} } @inproceedings{borstell:24026:sign-lang:lrec, author = {B{\"o}rstell, Carl}, title = {How to Approach Lexical Variation in Sign Language Corpora}, pages = {46--53}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24026.html}, doi = {10.63317/2y9y6az6dken}, abstract = {Looking at lexical frequency and, by extension, lexical variation is often among the first objectives after compiling a sign language corpus, since the only prerequisite is existing sign gloss annotations. However, measuring lexical frequency in a theoretically and statistically meaningful way can be a challenge. In this paper, I provide an overview of how to approach lexical variation in sign language corpora. The aim is to show ways of tackle lexical variation from different angles, from data collection to statistics and visualization, and how to motivate choices based on the data available and the research goals, thus serving as a practical guide for sign language corpus research. Drawing from previous work by different sign language corpus project teams, various approaches to measuring lexical variation are illustrated with data from the Swedish Sign Language (STS) Corpus, with examples that can easily be adapted to any sign language corpus.} } @inproceedings{desai:24045:sign-lang:lrec, author = {Desai, Aashaka and De Meulder, Maartje and Hochgesang, Julie A. and Kocab, Annemarie and Lu, Alex X.}, title = {Systemic Biases in Sign Language {AI} Research: A Deaf-Led Call to Reevaluate Research Agendas}, pages = {54--65}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24045.html}, doi = {10.63317/4qt6t64rxwd2}, abstract = {Growing research in sign language recognition, generation, and translation AI has been accompanied by calls for ethical development of such technologies. While these works are crucial to helping individual researchers do better, there is a notable lack of discussion of systemic biases or analysis of rhetoric that shape the research questions and methods in the field, especially as it remains dominated by hearing non-signing researchers. Therefore, we conduct a systematic review of 101 recent papers in sign language AI. Our analysis identifies significant biases in the current state of sign language AI research, including an overfocus on addressing perceived communication barriers, a lack of use of representative datasets, use of annotations lacking linguistic foundations, and development of methods that build on flawed models. We take the position that the field lacks meaningful input from Deaf stakeholders, and is instead driven by what decisions are the most convenient or perceived as important to hearing researchers. We end with a call to action: the field must make space for Deaf researchers to lead the conversation in sign language AI.} } @inproceedings{esselink:24042:sign-lang:lrec, author = {Esselink, Lyke and Oomen, Marloes and Roelofsen, Floris}, title = {Evaluating Inter-Annotator Agreement for Non-Manual Markers in Sign Languages}, pages = {66--76}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24042.html}, doi = {10.63317/5pduxds9maku}, abstract = {This paper is part of a larger project that aims to create a standardized procedure for annotating non-manual markers (NMMs) in sign language data. The paper describes two approaches to evaluating inter-annotator agreement, the event-based approach and the frame-based approach, and uses a combination of these two approaches to evaluate the annotation guidelines introduced in Oomen et al. (2023). The evaluation reveals that for several labels in the annotation scheme inter-annotator agreement is rather low. This indicates that the annotations guidelines need to be further improved. We present concrete recommendations for how this may be achieved, and intend to implement these recommendations in future work. All data and analysis scripts are available.} } @inproceedings{filhol:24016:sign-lang:lrec, author = {Filhol, Michael and von Ascheberg, Thomas}, title = {A software editor for the {AZVD} graphical Sign Language representation system}, pages = {77--85}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24016.html}, doi = {10.63317/4ih683d47twz}, abstract = {Based on real spontaneous productions by signers, AZVD is a graphical Sign Language representation system designed to maximise its potential for adoption by the signing community. Additionally, it is kept entirely synthesisable by construction, i.e. any AZVD content determines a signed output, which can be rendered through an avatar for example. This paper reports on the implementation of a software prototype developed to support AZVD editing, and the current extent of AZVD graphics integration. The point is to allow users to experience and discuss the AZVD approach, and ultimately assess it as a standardised grphical form for Sign Language representation.} } @inproceedings{gavrilescu:24037:sign-lang:lrec, author = {Gavrilescu, Robert and Geraci, Carlo and Mesch, Johanna}, title = {Content Questions in Sign Language -- From theory to language description via corpus, experiments, and fieldwork}, pages = {86--94}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24037.html}, doi = {10.63317/55edhht95q8o}, abstract = {The theory of language structure informs us about what we should expect when we want to investigate a certain construction. However, reality is often richer than what theories predict. In this study, we start from a theoretically informed set of hypotheses about the structure of wh-questions in sign language, we test them using a sign language corpus, a designed production experiment, and structured fieldwork in three sign languages, Swedish, Greek and French Sign Languages. The results will inform us on what type of contribution each research method can provide to reach accurate language descriptions.} } @inproceedings{halbout:24024:sign-lang:lrec, author = {Halbout, Julie and Fabre, Diandra and Ouakrim, Yanis and Lascar, Julie and Braffort, Annelies and Gouiff{\`e}s, Mich{\`e}le and Beautemps, Denis}, title = {{Matignon-LSF}: a Large Corpus of Interpreted {French} {Sign} {Language}}, pages = {95--101}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24024.html}, doi = {10.63317/42az5rxezs8a}, abstract = {In this paper we present Matignon-LSF, the first dataset of interpreted French Sign Language (LSF) and one of the largest LSF dataset available for research to date. This is a dataset of live interpreted LSF during public speeches by the French government. The dataset comprises 39 hours of LSF videos with French language audio and corresponding subtitles. In addition to this data, we offer pre-computed video features (I3D). We provide a detailed analysis of the proposed dataset as well as some experimental results to demonstrate the interest of this novel dataset.} } @inproceedings{hall:24010:sign-lang:lrec, author = {Hall, Kathleen Currie and Asthana, Anushka and Reid, Maggie and Gao, Yiran and Hobby, Grace and Tkachman, Oksana and Vesik, Kaili}, title = {Phonological Transcription of the Canadian Dictionary of {ASL} as a Language Resource}, pages = {102--110}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24010.html}, doi = {10.63317/43zzdod4xaiy}, abstract = {This paper introduces the ongoing project of digitizing and phonologically transcribing the The Canadian Dictionary of ASL to be used as a language resource. We describe the contents of the dictionary and the procedure used for creating the transcribed version, using the Sign Language Phonetic Annotator-Analyzer software. We also outline the benefits of creating a resource with such a detailed representation of the formational structure of signs.} } @inproceedings{imashev:24023:sign-lang:lrec, author = {Imashev, Alfarabi and Kydyrbekova, Aigerim and Mukushev, Medet and Sandygulova, Anara and Islam, Shynggys and Israilov, Khassan and Makazhanov, Aibek and Yessenbayev, Zhandos}, title = {Retrospective of {Kazakh-Russian} {Sign} {Language} Corpus Formation}, pages = {111--122}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24023.html}, doi = {10.63317/4mebvh4fp43n}, abstract = {Sign language (SL) is a mode of communication that, in most cases, relies on visual perception exclusively and utilizes visual-gestural modality. Sign languages are already universally acknowledged as complete and natural languages. The advent of machine learning techniques has expanded the range of potential applications, not only in industry but also in addressing societal needs. Previous research conducted before 2015 has already demonstrated encouraging outcomes in developing sign language recognition systems that are both quite accurate and resilient. Nevertheless, the effectiveness and utilization of algorithms are impacted not only by their accessibility but also, at times to a greater extent, by the presence of substantial quantities of pertinent data. At the commencement of the local sign language corpus collection in 2015, there was a notable deficit of local Kazakh-Russian sign language (K-RSL) data available for computer vision and machine-learning tasks. There were already corpora of another lexically close Russian Sign Langauge (RSL), but they were aimed at and tailored for research in linguistics. Therefore, we initiated the procedure by collecting pertinent data appropriate for machine-learning purposes. The subsets have been incorporated into the principal corpus and will be subject to future enhancements and refinements. This paper provides a concise overview of the collected components of the Kazakh-Russian Sign Language Corpus and the resulting outcomes derived from them within the last decade.} } @inproceedings{inoue:24022:sign-lang:lrec, author = {Inoue, Jundai and Miwa, Makoto and Sasaki, Yutaka and Hara, Daisuke}, title = {Enhancing Syllabic Component Classification in {Japanese} {Sign} {Language} by Pre-training on Non-Japanese Sign Language Data}, pages = {123--130}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24022.html}, doi = {10.63317/3om3rgzvhzd4}, abstract = {In sign languages, syllables are composed of syllabic components consisting of locations, movements, and handshapes; however, the rules of combinations of these syllabic components are still unclear. Decomposing existing syllables into syllabic components is necessary to clarify the rules. This study aims to construct an automatic syllabic component classification system for Japanese Sign Language (JSL) using deep learning. We propose a pre-training method using non-Japanese Sign Language data to achieve high performance in classifying syllabic components in a situation where the number of training JSL videos is limited. We also investigate multitask learning for syllabic component classification to share the information among the syllabic components. Experiments on the syllabic component classification for the dominant hand show that 1) pre-training with the American Sign Language (ASL) dataset improved classification performance for the movement and handshape components and 2) multitask learning did not contribute to the performance improvement of syllabic component classification. We also investigated the influence of pre-training on syllabic component classification by visualizing critical elements in videos to predict the components.} } @inproceedings{isard:24053:sign-lang:lrec, author = {Isard, Amy}, title = {Building Your Query Step by Step: A Query Wizard for the {MY} {DGS} -- {ANNIS} Portal of the {DGS} {Corpus}}, pages = {131--139}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24053.html}, doi = {10.63317/2qhs9oios7p3}, abstract = {MY DGS -- ANNIS makes the Public DGS Corpus available through the corpus query and visualization tool ANNIS. Due to the complex nature of the corpus, composing queries for advanced research questions can quickly become increasingly complicated. We present a Query Wizard which assists users in building valid queries for MY DGS -- ANNIS. Complex queries are built up from smaller blocks, which can be linked to each other through context-sensitive connections. Blocks provide options specific to a given annotation tier and dynamically lead users through their construction while preventing the creation of invalid queries. Once completed, queries can be opened directly in MY DGS -- ANNIS.} } @inproceedings{khan:24043:sign-lang:lrec, author = {Khan, Sarmad and Murtagh, Irene and McLoughlin, Simon D.}, title = {Investigating Motion History Images and Convolutional Neural Networks for Isolated {Irish} {Sign} {Language} Fingerspelling Recognition}, pages = {140--146}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24043.html}, doi = {10.63317/47rd3dyde3tc}, abstract = {The limited global competency in sign language makes the objective of improving communication for the deaf and hard-of-hearing community through computational processing both vital and necessary. In an effort to address this problem, our research leverages the Irish Sign Language hand shape (ISL-HS) dataset and state-of-the-art deep learning architectures to recognize the Irish Sign Language alphabet. We streamline the feature extraction methodology and pave the way for the efficient use of Convolutional Neural Networks (CNNs) by using Motion History Images (MHIs) for monitoring the sign language motions. The effectiveness of numerous powerful CNN architectures in deciphering the intricate patterns of motion captured in MHIs is investigated in this research. The process includes generating MHIs from the ISL dataset and then using these images to train several CNN neural network models and evaluate their ability to recognize the Irish Sign Language alphabet. The results demonstrate the possibility of investigating MHIs with advanced CNNs to enhance sign language recognition, with a noteworthy accuracy percentage. By contributing to the development of language processing tools and technologies for Irish Sign Language, this research has the potential to address the lack of technological communicative accessibility and inclusion for the deaf and hard-of-hearing community in Ireland.} } @inproceedings{kim:24028:sign-lang:lrec, author = {Kim, Jung-Ho and Ko, Changyong and Huerta-Enochian, Mathew and Ko, Seung Yong}, title = {Shedding Light on the Underexplored: Tackling the Minor Sign Language Research Topics}, pages = {147--158}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24028.html}, doi = {10.63317/274tf6jgtgqh}, abstract = {In the past decade, sign language research has achieved remarkable results alongside the advancements in deep learning. However, there is a disconnect between the outcomes of these research efforts and the actual use of sign language by signers. In this position paper, we reviewed sign language papers related to deep learning published in the last ten years to explore reasons for this gap. We found many areas of research that are still underdeveloped, despite their linguistic importance. Based on an analysis of known corpora and methodologies, we identified the reasons for the lack of progress in these areas and propose directions for future research efforts.} } @inproceedings{kimmelman:24008:sign-lang:lrec, author = {Kimmelman, Vadim and Oomen, Marloes and Pfau, Roland}, title = {Headshakes in {NGT}: Relation between Phonetic Properties {\&} Linguistic Functions}, pages = {159--167}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24008.html}, doi = {10.63317/4eew3sj6ypi4}, abstract = {Non-manual markers (such as facial expressions and head movements) have been shown to fulfil a wide range of grammatical functions across sign languages. One nonmanual marker that is very wide-spread is headshake used to express negation. While negation and headshake have been studied for a variety of sign languages, phonetic/kinematic research on headshake has been mostly absent. In this paper, we conduct a phonetic analysis of headshake in Sign Language of the Netherlands using a Computer Vision solution, namely OpenFace. We specifically analyze whether linguistic properties of headshake (e.g. spreading and the type of signs co-occurring with the headshake) influence its phonetic form.} } @inproceedings{kimmelman:24009:sign-lang:lrec, author = {Kimmelman, Vadim and Price, Ari and Safar, Josefina and de Vos, Connie and Bulla, Jan}, title = {Nonmanual Marking of Questions in {Balinese} Homesign Interactions: a Computer-Vision Assisted Analysis}, pages = {168--177}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24009.html}, doi = {10.63317/5aur9arxz9vb}, abstract = {In recent years, both linguistic resources and computer-based tools have been developed that make it possible to investigate research questions that have not been studied before. In this study, we conduct a study of nonmanual question marking, using data from the Balinese Homesign Corpus -- a unique resource documenting language use in several Balinese homesigners. We further demonstrate how using OpenFace, a Computer-Vision solution, allows for quantitative analysis of head tilts used by these signers in marking questions. We also showcase a pilot statistical analysis of the dynamic kinetic contours of the head movements.} } @inproceedings{klomp:24036:sign-lang:lrec, author = {Klomp, Ulrika and Gierman, Lisa and Manders, Pieter and Nauta, Ellen Yassine and Otterspeer, Gom{\`e}r and Pelupessy, Ray and Stern, Galya and Venter, Dalene and Wubbolts, Casper and Oomen, Marloes and Roelofsen, Floris}, title = {An Extension of the {NGT} Dataset in {Global} {Signbank}}, pages = {178--183}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24036.html}, doi = {10.63317/3ooj2j799q63}, abstract = {To support language documentation, linguistic research, and acquisition of Sign Language of the Netherlands (NGT), we are expanding the NGT dataset in the lexical database Global Signbank. Our most prioritized goal is to add ca. 11,000 glosses (entries). We further aim at adding ca. 3,000 example sentences and to provide linguistic information with as many glosses as possible. As for linguistic information, Signbank allows for extensive phonological descriptions of signs, and the addition of multiple senses per sign, which we would like to connect to synsets in the Multilingual Sign Language Wordnet. Additionally, we are recording extra video data: we make multiple videos of the same sign, taken from different angles, and videos with non-manual expressions. Furthermore, we are collecting motion capture data, for improved (automatic) sign language recognition and production in the future. In this paper, we describe how we proceed, the decisions that have been made so far, and future uses of the dataset.} } @inproceedings{konrad:24050:sign-lang:lrec, author = {Konrad, Reiner and Hanke, Thomas and Isard, Amy and Schulder, Marc and K{\"o}nig, Lutz and Bleicken, Julian and B{\"o}se, Oliver}, title = {Corpus {\`a} la carte -- Improving Access to the {Public} {DGS} {Corpus}}, pages = {184--193}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24050.html}, doi = {10.63317/2owwcdi3rvu5}, abstract = {This article presents the fourth release of the Public DGS Corpus, a large corpus of German Sign Language (DGS). Since its first release in 2018, the Public DGS Corpus has provided its content through multiple portals to meet the needs of different user groups. Having started with a community portal and a research portal for general data access, the ANNIS portal for dynamic web-based exploration of the corpus was added in 2022. With this latest release, a fourth portal is added to allow sign language linguists to access the public corpus directly through the annotation software iLex. Furthermore, search capabilities and interconnectedness between the portals are strongly improved, allowing users to move between portals to combine their strengths. Additional improvements to the corpus include additional recordings, new pose information models, improved HamNoSys, enhanced type information and web interface revisions.} } @inproceedings{langer:24039:sign-lang:lrec, author = {Langer, Gabriele and M{\"u}ller, Anke and W{\"a}hl, Sabrina and Otte, Felicitas and Sepke, Lea and Hanke, Thomas}, title = {Introducing the {DW-DGS} -- The Digital Dictionary of {DGS}}, pages = {194--203}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24039.html}, doi = {10.63317/3pgjsvpbojdk}, abstract = {This article describes the lexical resource DW-DGS -- the first corpus-based digital dictionary of German Sign Language (DGS). Basic information is provided on dictionary type, context of compilation, sign representation in the product, metalanguage, dictionary content, information types displayed in entries, and dictionary structure. The article also provides an overview on data sources, methods, workflow procedures, and tools used in the lexicographic process. Challenges of making a corpus-based sign language dictionary and solutions developed for the DW-DGS are mentioned. The aim of this contribution is to provide an overview on the resource. It also serves as a starting point by referring to papers that describe the structures and procedures of the DW-DGS in more depth.} } @inproceedings{lascar:24012:sign-lang:lrec, author = {Lascar, Julie and Gouiff{\`e}s, Mich{\`e}le and Braffort, Annelies and Danet, Claire}, title = {Annotation of {LSF} subtitled videos without a pre-existing dictionary}, pages = {204--212}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24012.html}, doi = {10.63317/2jphxdy2yx9j}, abstract = {This paper proposes a method for the automatic annotation of lexical units in LSF videos, using a subtitled corpus without annotation. This method based on machine learning and involving linguists for added precision and reliability, comprises several stages. The first consists of building a bilingual lexicon (including potential variants of a given lexical unit) in a weakly supervised manner. The resulting lexicon is then refined and cleaned by LSF experts. This data serves next to train a supervised classifier for automatic annotation of lexical units on the Mediapi-RGB corpus. Our Pytorch implementation is publicly available.} } @inproceedings{malaia:24049:sign-lang:lrec, author = {Malaia, Evie A. and Borneman, Joshua and Gurbuz, Sevgi}, title = {Capturing Motion: Using Radar to Build Better Sign Language Corpora}, pages = {213--218}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24049.html}, doi = {10.63317/4z47r9gyz78m}, abstract = {Sign language conveys information using dynamic visual signal. Proficient signers rely on the skill in processing and predictive motion information during sign language comprehension. Much current work in sign language corpora development relies on video data. However, from the perspective of information transfer in communication, video recordings are limited in capturing spatial and temporal frequencies of sign language signal in sufficient resolution. In contrast, radar can capture 3D motion data at high temporal and spatial resolution, preserving depth articulations lost in 2D video. Radar's recording parameters can also be adapted in real time to optimize temporal resolution for rapid signing motions. Thus, radar recordings provide higher-fidelity corpora for analyzing linguistic features of sign languages and creating smart environments that respond to signed input. Crucially, radar recordings uphold user privacy, only capturing kinematic parameters of communicative signal, as opposed to signer identity. Radar resolution in capturing dynamic data from sign language production, and privacy advantages it provides to users, make it uniquely suited for advancing sign language research through corpora development.} } @inproceedings{malmberg:24047:sign-lang:lrec, author = {Malmberg, Fredrik and Klezovich, Anna and Mesch, Johanna and Beskow, Jonas}, title = {Exploring Latent Sign Language Representations with Isolated Signs, Sentences and In-the-Wild Data}, pages = {219--224}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24047.html}, doi = {10.63317/3mbacm3mk4iq}, abstract = {Unsupervised representation learning offers a promising way of utilising large unannotated sign language resources found on the Internet. In this paper, a VQ-VAE model is trained to learn a codebook of motion primitives from sign language data. For training, we use isolated signs and sentences from a sign language dictionary. Three models are trained: one on isolated signs, one on sentences, and one mixed model. We test these models by comparing how well they are able to reconstruct held-out data from the dictionary, as well as an in-the-wild dataset based on sign language videos from YouTube. These data are characterized by less formal and more expressive signing than the dictionary items. Results show that the isolated sign model yields considerably higher reconstruction loss for the YouTube dataset, while the sentence model performs the best on this data. Further, an analysis of codebook usage reveals that the set of codes used by isolated signs and sentences differ significantly. In order to further understand the different character of the datasets, we carry out an analysis of the velocity profiles, which reveals that signing data in-the-wild has much higher average velocity than dictionary signs and phrases. We believe these differences also explain the large differences in reconstruction loss observed.} } @inproceedings{martinezguevara:24027:sign-lang:lrec, author = {Mart{\'i}nez-Guevara, Niels and Curiel, Arturo}, title = {Quantitative Analysis of Hand Locations in both Sign Language and Non-linguistic Gesture Videos}, pages = {225--234}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24027.html}, doi = {10.63317/4kupnuhhgusr}, abstract = {This paper explores whether measurable quantitative linguistic relationships are readily apparent in the use of space of three different Sign Languages (SLs): British Sign Language (BSL), Dutch Sign Language (NGT) and Mexican Sign Language (LSM). To this end, three SL datasets were collected; one for each of the languages of interest. Informative video frames were extracted from the collected datasets, which in turn were automatically processed to detect hand locations. The obtained information was analyzed through statistical methods, and compared against a dataset of non-linguistic gestural communication: the latter, in an effort to observe whether space-use differs between linguistic and non-linguistic gestures. The results show that meaningful gestures---regardless of whether they are deemed linguistic or not---seem to induce a spatial hierarchy around the gesturer, disproportionately favoring certain areas during articulation. SLs in particular seem to exert pressure on those areas to become more efficient, as signers appear to concentrate hand activity over more cohesive regions than non-signers. In addition, these results point towards an indirect relationship between culturally-recognized gestures and their surrounding SLs, showing that there is still work to be done on the exploration of iconicity and its effects on gestural communication.} } @inproceedings{martinod:24038:sign-lang:lrec, author = {Martinod, Emmanuella and Filhol, Michael}, title = {Formal Representation of Interrogation in {French} {Sign} {Language}}, pages = {235--243}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24038.html}, doi = {10.63317/4gbavdj4enwm}, abstract = {This paper concerns the marking of interrogation in French Sign Language (LSF). Early work on Sign Languages (SLs) underlined the role of non-manual elements in the production of interrogatives. Studies often point to the role of eyebrows depending on the type of question: eyebrows would usually be raised for the production of yes/no questions, while they would be lowered for other types of questions. For LSF, previous studies seem to validate this contrast. We tested this thoroughly in the framework of AZee, a formal approach to SL modeling based on the identification of linguistic associations between forms and identified meanings, called production rules. We present our methodology to extract AZee production rules, consisting of data searches alternating form and meaning criteria gradually converging to strong associations, ultimately leading to production rules. Our results (i) show no link between raised or lowered eyebrows and a specific type of question, (ii) highlight instead the role of another non-manual marker: the advancement of the chin. However, since eyebrows remain frequently involved in the analyzed questions (all types included), we intend to further focus on the potential role of the signer's expectations while formulating his request.} } @inproceedings{mcdonald:24018:sign-lang:lrec, author = {McDonald, John C. and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Wolfe, Rosalee}, title = {Multilingual Synthesis of Depictions through Structured Descriptions of Sign: An Initial Case Study}, pages = {244--253}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24018.html}, doi = {10.63317/2wzky9so2vix}, abstract = {Sign language synthesis systems must contend with an enormous variety of possible target languages across the world, and in many locations, such as Europe, the number of sign languages that can be found in a relatively limited geographical area can be surprising. For such a synthesis system to be widely useful, it must not be limited to only one target language. This presents challenges both for the linguistic models and the animation systems that drive these displays. This paper presents a case study for animating discourse in three target languages, French, Greek and German, generated directly from the same base linguistic description. The case study exploits non-lexical constructs in sign, which are more common among sign languages, while providing a first step for synthesizing those aspects that are different. Further, it suggests a possible path forward to exploring whether linguistic structures in one sign language can be exploited in other sign languages, which might be particularly helpful in under-resourced languages.} } @inproceedings{mesch:24007:sign-lang:lrec, author = {Mesch, Johanna and Bj{\"o}rkstrand, Thomas and Balkstam, Eira and Hansson, Patrick and Riemer Kankkonen, Nikolaus}, title = {{Swedish} {Sign} {Language} Resources from a User's Perspective}, pages = {254--261}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24007.html}, doi = {10.63317/3tbeozhtobw8}, abstract = {The Swedish Sign Language Dictionary [Svenskt teckenspr{\aa}kslexikon] is one of the most visited websites at Stockholm University, with four million visits each year. The dictionary is an easy-to-use resource for the community, families, relatives, students, educators, researchers and other stakeholders that can be accessed through the website, app, and mobile platforms. STS-korpus is an online interface for the Swedish Sign Language Corpus that is linked to the STS Dictionary, enhancing its utility. Other applications, like TSP Quiz and the STS transcription tool, will also be evaluated. In January 2024, we conducted a survey to explore how users utilise Swedish sign language resources in their everyday lives, studies and work, regardless of hearing status and sign language skills. The purpose is to evaluate these resources from a user's perspective, including aspects such as user-friendliness, relevance, comprehensibility and effectiveness in aiding language learning or communication.} } @inproceedings{miyazaki:24004:sign-lang:lrec, author = {Miyazaki, Taro and Tan, Sihan and Uchida, Tsubasa and Kaneko, Hiroyuki}, title = {Sign Language Translation with Gloss Pair Encoding}, pages = {262--268}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24004.html}, doi = {10.63317/3mfuq8ycz24e}, abstract = {Because sign languages are the first language for those who are born deaf or who lost their hearing in early childhood, it is better to use sign languages rather than transcribed spoken language to provide important information to these people. We have been developing a sign language computer graphics generation system to provide information to deaf people, and in this paper, we present a translation method from spoken language to sign language that can be used in the system. In general, since the number of glosses used when transcribing sign language is limited, a single meaning is often expressed by a combination of multiple sign words, i.e., the word "library" is expressed in Japanese Sign Language with two words: "book" and "building." To merge these expressions into one token, we propose gloss pair encoding (GPE), which is inspired by bite pair encoding (BPE). This technique is expected to enable more accurate handling of expressions that have a single meaning in multiple sign words. We also show that it is effective as data augmentation on the sign language side in sign language translation, which has not been done much so far.} } @inproceedings{otterspeer:24044:sign-lang:lrec, author = {Otterspeer, Gom{\`e}r and Klomp, Ulrika and Roelofsen, Floris}, title = {{SignCollect}: A `Touchless' Pipeline for Constructing Large-scale Sign Language Repositories}, pages = {269--275}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24044.html}, doi = {10.63317/3maz9vncwzo9}, abstract = {The projectteam of the Signbank project at the University of Amsterdam intends to substantially extend the NGT lexicon in Global Signbank within a limited timespan. To make this possible, the signCollect platform was developed to automate a major part of the workflow. The signCollect system includes a `touchless' interface which enables a signer to control the system through simple gestures (recognized using computer vision) to (i) prompt the display of the next gloss, (ii) start a new recording, and (iii) approve/disapprove a recording. This capability allows a signer to record between 60 to 120 signs per hour, without the need for any assisting staff to be present. The approved recordings immediately become visible in the signCollect database, so that other members of the team can add metadata. With feedback from workshop participants we intend to further optimize the signCollect platform and make it available as an open-source tool for all sign language research teams.} } @inproceedings{picron:24021:sign-lang:lrec, author = {Picron, Frankie and Van Landuyt, Davy and Omardeen, Rehana and Efthimiou, Eleni and Wolfe, Rosalee and Fotinea, Stavroula-Evita and Goulas, Theodoros and Tismer, Christian and Kopf, Maria and Hanke, Thomas}, title = {The {EASIER} Mobile Application and Avatar End-User Evaluation Methodology}, pages = {276--281}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24021.html}, doi = {10.63317/3ujwci4s83h3}, abstract = {Here we report on the methodological approach adopted for the end-user evaluation studies carried out during the lifecycle of the EASIER project, focusing on the project's mobile app and avatar technologies. Evaluation was performed in two cycles and involved both deaf signers' and hearing sign language (SL) experts' groups from five SLs to provide user feedback, which served as a reference to base the next development steps of the respective EASIER components. With this goal in mind, priorities were (i) to exploit information gathered via focus group discussions after (ii) presenting evaluators with the technological components and related questionnaires fully accessible to signers to maximize feedback and underline the importance of user involvement in the development of the technology.} } @inproceedings{rathmann:24002:sign-lang:lrec, author = {Rathmann, Christian and Quadros, Ronice M{\"u}ller de and Gei{\ss}ler, Thomas and Peters, Christian and Fernandes, Francisco and Loio, Milene Peixer and Fran{\c c}a, Diego}, title = {{VisuoLab}: Building a sign language multilingual, multimodal and multifunctional platform}, pages = {282--289}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24002.html}, doi = {10.63317/59o9d9e78s5j}, abstract = {VisuoLab is a multifunctional, multimodal and multilingual platform designed for sign language communities. This platform is based on web accessibility and usability, and is specifically designed in a visual way. All resources are organized to be available in sign languages and written languages for different purposes: to provide materials related to and in sign languages, to produce materials (such as papers, video books, teaching materials that include signing production), to teach with signing tools, to interpret and translate activities for training purposes, and to evaluate signing progress. VisuoLab is designed as an open source platform. The current stage of VisuoLab is a beta version available in the development area of Levante Lab for the platform: https://visuolab.levantelab.com.br/} } @inproceedings{ranum:24030:sign-lang:lrec, author = {Ranum, Oline and Otterspeer, Gom{\`e}r and Andersen, Jari I. and Belleman, Robert G. and Roelofsen, Floris}, title = {{3D-LEX} v1.0 -- {3D} Lexicons for {American} {Sign} {Language} and {Sign} {Language} of the {Netherlands}}, pages = {290--301}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24030.html}, doi = {10.63317/4gepxuonnfdc}, abstract = {In this work, we present an efficient approach for capturing sign language in 3D, introduce the 3D-LEX v1.0 dataset, and detail a method for semi-automatic annotation of phonetic properties. Our procedure integrates three motion capture techniques encompassing high-resolution 3D poses, 3D handshapes, and depth-aware facial features, to attain an average sampling rate of one sign every 10 seconds. This includes the time for presenting a sign example, performing and recording the sign, and archiving the capture. The 3D-LEX dataset includes 1,000 signs from American Sign Language and an additional 1,000 signs from the Sign Language of the Netherlands. We showcase the dataset utility by presenting a simple method for generating handshape annotations directly from 3D-LEX. We produce handshape labels for 1,000 signs from American Sign Language and evaluate the labels in a sign recognition task. The labels enhance gloss recognition accuracy by 5{\%} over using no handshape annotations, and by 1{\%} over expert annotations. Our motion capture data supports in-depth analysis of sign features and facilitates the generation of 2D projections from any viewpoint. The 3D-LEX collection has been aligned with existing sign language benchmarks and linguistic resources, to support studies in 3D-aware sign language processing.} } @inproceedings{quadros:24001:sign-lang:lrec, author = {Quadros, Ronice M{\"u}ller de and Rathmann, Christian and Romanek, P{\'e}ter Zal{\'a}n and Fernandes, Francisco and Cond{\'e}, Sther}, title = {{Signbank} 2.0 of Sign Languages: Easy to Administer, Easy to Use, Easy to Share}, pages = {302--314}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24001.html}, doi = {10.63317/4niw9buxjpvu}, abstract = {Signbank 2.0 integrates sign language documentation to identify signs with their specifications in the context of a large sign language corpus. Signbank 2.0 is inspired by Global Signbank, especially with respect to the integration of the general linguistic structure, and by developments from the earlier Libras Sign Identification platform, with search systems organized by sign language parameters. The current proposal presents several advances, especially regarding the administration panel with a simple dashboard. In addition, the current Signbank 2.0 implements [and at least one more instance] more sophisticated search systems from a linguistic and technological point of view. The tools developed include more possibilities for sign searches categorized based on linguistic and visual criteria. Finally, the search system presents the frequency of signs linked to the EAF files, listing the occurrences in the integrated corpus and giving the exact video timing of the sign.} } @inproceedings{reverdy:24031:sign-lang:lrec, author = {Reverdy, Cl{\'e}ment and Gibet, Sylvie and Le Naour, Thibaut}, title = {{STK} {LSF}: A Motion Capture Dataset in {LSF} for {SignToKids}}, pages = {315--322}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24031.html}, doi = {10.63317/4y9dcusqas55}, abstract = {This article presents a new bilingual dataset in written French and French Sign Language (LSF), called STK LSF. This corpus is currently being produced as part of the ANR SignToKids project. The aim of this corpus is to provide digital educational tools for deaf children, thereby facilitating the joint learning of LSF and written French. More broadly, it is intended to support future studies on the automatic processing of signed languages. To define this corpus, we focused on several grammatical phenomena typical to LSF, as well as in tales usually studied by hearing children in the second cycle in France. The corpus data represent approximately 1 hour of recording, carried out with a motion capture system (MoCap) offering a spatial precision of less than 1 mm and a temporal precision of 240 Hz. This high level of precision guarantees the quality of the data collected, which will be used both to build pedagogical scenarios in French and LSF, including signing avatar videos, and for automatic translation of text into LSF.} } @inproceedings{roh:24052:sign-lang:lrec, author = {Roh, Kyunggeun and Lee, Huije and Hwang, Eui Jun and Cho, Sukmin and Park, Jong C.}, title = {Preprocessing Mediapipe Keypoints with Keypoint Reconstruction and Anchors for Isolated Sign Language Recognition}, pages = {323--334}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24052.html}, doi = {10.63317/39tdbta3r9wc}, abstract = {Isolated Sign Language Recognition (ISLR) aims to classify signs into the corresponding gloss, but it remains challenging due to rapid movements and minute changes of hands. Pose-based approaches, recently gaining attention due to their robustness against the environment, are crucial against such challenging movements and changes due to the diculty of capturing small joint movements from the noisy keypoints. In this work, we emphasize the importance of preprocessing keypoints to alleviate the risk of such errors. We employ normalization using anchor points to accurately track the relative motion of skeletal joints, focusing on hand movements. Additionally, we implement bilinear interpolation to reconstruct keypoints, particularly to retrieve missing information for hands that were not detected. Preprocessing methods proposed in this work show a 6.05{\%} improvement in accuracy and achieved 83.26{\%} accuracy with data augmentation on the WLASL dataset, which is the highest among pose-based approaches. The proposed methods show strengths in cases with signs having importance in the hand shape, especially when some frames have undetected hands.} } @inproceedings{sahin:24040:sign-lang:lrec, author = {{\c S}ahin, Karahan and G{\"o}kg{\"o}z, Kadir}, title = {Decoding Sign Languages: The {SL-FE} Framework for Phonological Analysis and Automated Annotation}, pages = {335--342}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24040.html}, doi = {10.63317/4gxd4idrhodw}, abstract = {A novel framework for theory-driven annotation and analysis for Sign Languages. This framework provides both continuous representations for phonological information and discrete labels for annotating sign language videos. With this framework, we were able to derive a phonological phenomenon, namely Dominance, and Symmetry by defining a ranking function for calculating phonological complexity and resulting in high-accuracy retrieval for Turkish Sign Language (TID).} } @inproceedings{schulder:24034:sign-lang:lrec, author = {Schulder, Marc and Bigeard, Sam and Kopf, Maria and Hanke, Thomas and Kuder, Anna and W{\'o}jcicka, Joanna and Mesch, Johanna and Bj{\"o}rkstrand, Thomas and Vacalopoulou, Anna and Vasilaki, Kyriaki and Goulas, Theodoros and Fotinea, Stavroula-Evita and Efthimiou, Eleni}, title = {Signs and Synonymity: Continuing Development of the {Multilingual} {Sign} {Language} {Wordnet}}, pages = {343--353}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24034.html}, doi = {10.63317/4mvt6a6nhif3}, abstract = {The Multilingual Sign Language Wordnet is the first publicly available wordnet resource for sign languages. It is a growing multilingual resource providing data for eight sign languages to date. During the initial phase of its creation, the focus lay on producing the infrastructure to support various languages and to produce initial sets of content for them. This article represents the start of the second phase, in which the focus is moved to establishing overlapping coverage across the different sign languages. Building on the data produced so far, a new feature to assist annotation is introduced which leverages established partial synonymy between signs (inter- and cross-lingually) to discover likely additional synonymies. Other improvements to the annotation interface and workflow build directly on the experiences from the first phase. Working with the updated annotation interface, new data is produced for Polish Sign Language, Greek Sign Language and Swedish Sign Language.} } @inproceedings{sharma:24041:sign-lang:lrec, author = {Sharma, Paritosh and Challant, Camille and Filhol, Michael}, title = {Facial Expressions for Sign Language Synthesis using {FACSHuman} and {AZee}}, pages = {354--360}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24041.html}, doi = {10.63317/59kppqpc7bvr}, abstract = {This paper presents an approach to synthesising facial expressions on signing avatars. We implement those generated by a recently proposed set of rules formalised in the AZee framework for LSF. Our methodology combines computer vision, linguistic insights, and morph target animation to address the challenges posed by the synthesis of nuanced facial expressions, which are pivotal for conveying emotions and grammatical cues in sign language. By implementing a set of universally applicable morphs and incorporating these advancements into our animation system, we aim to improve the realism and expressiveness of signing avatars. Our findings suggest an enhancement in the synthesis of non-manual signals, which extends to multiple avatars. This work opens new avenues for future research, including the exploration of more sophisticated facial modelling techniques and the potential integration of facial motion capture data to refine the animation of facial expressions further.} } @inproceedings{susman:24005:sign-lang:lrec, author = {Susman, Margaux and Kimmelman, Vadim}, title = {Eye Blink Detection in Sign Language Data Using {CNNs} and Rule-Based Methods}, pages = {361--369}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24005.html}, doi = {10.63317/4oxyyek4f24q}, abstract = {Eye blinks are used in a variety of sign languages as prosodic boundary markers. However, no cross-linguistic quantitative research on eye blinks exists. In order to facilitate such research in future, we develop and test different methods of automatic eyeblink identification, based on a linguistic definition of blinks, and in a dataset of a natural sign language (French Sign Language). We compare two main approaches to eye openness detection: calculating the Eye Aspect Ratio using MediaPipe, and training CNNs to detect openness directly based on images from the video recordings. For the CNN method, we train different models (with different numbers of signers in the training data, different frame crops and different numbers of epochs). We then combine the openness degree detection with a separate rule-based component in order to determine boundaries of blink events. We demonstrate that both methods perform relatively well, and discuss the practical implications of the methods.} } @inproceedings{tan:24006:sign-lang:lrec, author = {Tan, Sihan and Miyazaki, Taro and Itoyama, Katsutoshi and Nakadai, Kazuhiro}, title = {{SEDA}: Simple and Effective Data Augmentation for Sign Language Understanding}, pages = {370--375}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24006.html}, doi = {10.63317/28bctqifudvv}, abstract = {Sign language understanding (SLU) aims to convert sign language videos into glosses that transcribe sign language word-by-word by means of another written language and generate corresponding spoken sentences, including sign language recognition (SLR) and sign language translation (SLT). SLU has been a challenging undertaking since it demands the capability of fine-grained video understanding and sequence generation. In addition, the lack of supervised training data further hinders the advancement of SLU. To narrow the modality gap between vision and language and mitigate the data scarcity problem, we propose a Simple and Effective Data Augmentation (SEDA) framework for end-to-end SLU. In particular, SEDA consists of two key components: data augmentations on both sign and text sides and multi-task learning with task-specific fine-tuning. Experimental results on RWTH-PHOENIX Weather 2014T demonstrate that our proposed SEDA framework significantly and consistently outperforms the baseline model and achieves a WER of 19.91, a BLEU score of 25.19, and a ROUGE score of 51.72, delivering competitive scores in both SLR and SLT.} } @inproceedings{uchida:24011:sign-lang:lrec, author = {Uchida, Tsubasa and Miyazaki, Taro and Kaneko, Hiroyuki}, title = {{HamNoSys-based} Motion Editing Method for Sign Language}, pages = {376--385}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24011.html}, doi = {10.63317/2yvyqhtxo9rn}, abstract = {We have developed a Japanese-to-Japanese Sign Language (JSL) translation system to expand sign language services for the Deaf. Although recording the motion data of isolated JSL by motion capture (MoCap) and avatar animation driven by MoCap data is effective for capturing the more natural movements of sign language, the disadvantage is that they lack the flexibility to reproduce the contextual modification of signs. We therefore propose a sign language motion data editing method based on the Hamburg Notation System for Sign Languages (HamNoSys) for use in a hybrid system that combines a MoCap data-driven technique and a phonological generation technique. The proposed method enables the editing of handshape, hand orientation, and location of the motion data based on HamNoSys components to generate contextual modifications for motion-captured citation form signs in translated gloss sequences. Experimental results demonstrate that our method achieves the flexibility to generate contextual modifications and new movements while preserving natural human-like movements without the need for additional MoCap processes.} } @inproceedings{vazquezenriquez:24033:sign-lang:lrec, author = {V{\'a}zquez-Enr{\'i}quez, Manuel and Alba-Castro, Jos{\'e} Luis and P{\'e}rez-P{\'e}rez, Ania and Cabeza-Pereiro, Mar{\'i}a del Carmen and Doc{\'i}o-Fern{\'a}ndez, Laura}, title = {{SignaMed}: a Cooperative Bilingual {LSE-Spanish} Dictionary in the Healthcare Domain}, pages = {386--394}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24033.html}, doi = {10.63317/3ic8sg76puzk}, abstract = {In this paper we present SignaMed, a bilingual dictionary accessible in Spanish and LSE (Spanish Sign Language) specific to the medical domain. Building a sign language dataset to develop machine learning algorithms and linguistic studies is a complex task that requires the cooperation of Deaf people. The dictionary platform, built with their contributions, offers diverse access modes for users, including basic search functionalities, games, and activities for sign donation. It allows sign searching using webcam or mobile phone capturing, facilitating intuitive interaction and feedback. The article presents the technical, linguistic and cooperation details behind the construction of the dictionary and will hopefully serve as inspiration for similar initiatives in other sign languages. The dictionary is accessible through https://signamed.web.app.} } @inproceedings{xia:24014:sign-lang:lrec, author = {Xia, Zhaoyang and Zhou, Yang and Han, Ligong and Neidle, Carol and Metaxas, Dimitris}, title = {Diffusion Models for Sign Language Video Anonymization}, pages = {395--407}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24014.html}, doi = {10.63317/45yijutfouih}, abstract = {Since American Sign Language (ASL) has no standard written form, Deaf signers frequently share videos in order to communicate in their native language. However, this does not preserve privacy. Since critical linguistic information is transmitted through facial expressions, the face cannot be obscured. While signers have expressed interest, for a variety of applications, in sign language video anonymization that would effectively preserve linguistic content, attempts to develop such technology have had limited success and generally require pose estimation that cannot be readily carried out in the wild. To address current limitations, our research introduces DiffSLVA, a novel methodology that uses pre-trained large-scale diffusion models for text-guided sign language video anonymization. We incorporate ControlNet, which leverages low-level image features such as HED (Holistically-Nested Edge Detection) edges, to circumvent the need for pose estimation. Additionally, we develop a specialized module to capture linguistically essential facial expressions. We then combine the above methods to achieve anonymization that preserves the essential linguistic content of the original signer. This innovative methodology makes possible, for the first time, sign language video anonymization that could be used for real-world applications, which would offer significant benefits to the Deaf and Hard-of-Hearing communities.} } @inproceedings{zhou:24015:sign-lang:lrec, author = {Zhou, Yang and Xia, Zhaoyang and Chen, Yuxiao and Neidle, Carol and Metaxas, Dimitris}, title = {A Multimodal Spatio-Temporal {GCN} Model with Enhancements for Isolated Sign Recognition}, pages = {408--419}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources}, maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {25}, month = may, year = {2024}, isbn = {978-2-493814-30-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24015.html}, doi = {10.63317/5jojxksciv3h}, abstract = {We propose a multimodal network using skeletons and handshapes as input to recognize individual signs and detect their boundaries in American Sign Language (ASL) videos. Our method integrates a spatio-temporal Graph Convolutional Network (GCN) architecture to estimate human skeleton keypoints; it uses a late-fusion approach for both forward and backward processing of video streams. Our (core) method is designed for the extraction---and analysis of features from---ASL videos, to enhance accuracy and efficiency of recognition of individual signs. A Gating module based on per-channel multi-layer convolutions is employed to evaluate significant frames for recognition of isolated signs. Additionally, an auxiliary multimodal branch network, integrated with a transformer, is designed to estimate the linguistic start and end frames of an isolated sign within a video clip. We evaluated performance of our approach on multiple datasets that include isolated, citation-form signs and signs pre-segmented from continuous signing based on linguistic annotations of start and end points of signs within sentences. We have achieved very promising results when using both types of sign videos combined for training, with overall sign recognition accuracy of 80.8{\%} Top-1 and 95.2{\%} Top-5 for citation-form signs, and 80.4{\%} Top-1 and 93.0{\%} Top-5 for signs pre-segmented from continuous signing.} } @proceedings{lrec:sign-lang:22, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, title = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, url = {http://www.lrec-conf.org/proceedings/lrec2022/workshops/signlang/2022.signlang-1.0.pdf}, doi = {10.63317/2rifm6bf4efz} } @inproceedings{bejarano:22013:sign-lang:lrec, author = {Bejarano, Gissella and Huamani-Malca, Joe and Cerna-Herrera, Francisco and Alva-Manchego, Fernando and Rivas, Pablo}, title = {{PeruSIL}: A Framework to Build a Continuous {Peruvian} {Sign} {Language} Interpretation Dataset}, pages = {1--8}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22013.html}, doi = {10.63317/2fnsdpgwqaks}, abstract = {Video-based datasets for Continuous Sign Language are scarce due to the challenging task of recording videos from native signers and the reduced number of people who can annotate sign language. COVID-19 has evidenced the key role of sign language interpreters in delivering nationwide health messages to deaf communities. In this paper, we present a framework for creating a multi-modal sign language interpretation dataset based on videos and we use it to create the first dataset for Peruvian Sign Language (LSP) interpretation annotated by hearing volunteers who have intermediate knowledge of PSL guided by the video audio. We rely on hearing people to produce a first version of the annotations, which should be reviewed by native signers in the future. Our contributions: i) we design a framework to annotate a sign Language dataset; ii) we release the first annotated LSP multi-modal interpretation dataset (AEC); iii) we evaluate the annotation done by hearing people by training a sign language recognition model. Our model reaches up to 80.3{\%} of accuracy among a minimum of five classes (signs) AEC dataset, and 52.4{\%} in a second dataset. Nevertheless, analysis by subject in the second dataset show variations worth to discuss.} } @inproceedings{bigeard:22036:sign-lang:lrec, author = {Bigeard, Sam and Schulder, Marc and Kopf, Maria and Hanke, Thomas and Vasilaki, Kyriaki and Vacalopoulou, Anna and Goulas, Theodoros and Dimou, Athanasia-Lida and Fotinea, Stavroula-Evita and Efthimiou, Eleni}, title = {Introducing Sign Languages to a Multilingual Wordnet: Bootstrapping Corpora and Lexical Resources of {Greek} {Sign} {Language} and {German} {Sign} {Language}}, pages = {9--15}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22036.html}, doi = {10.63317/4rue6p9a97i7}, abstract = {Wordnets have been a popular lexical resource type for many years. Their sense-based representation of lexical items and numerous relation structures have been used for a variety of computational and linguistic applications. The inclusion of different wordnets into multilingual wordnet networks has further extended their use into the realm of cross-lingual research. Wordnets have been released for many spoken languages. Research has also been carried out into the creation of wordnets for several sign languages, but none have yet resulted in publicly available datasets. This article presents our own efforts towards an inclusion of sign languages in a multilingual wordnet, starting with Greek Sign Language (GSL) and German Sign Language (DGS). Based on differences in available language resources between GSL and DGS, we trial two workflows with different coverage priorities. We also explore how synergies between both workflows can be leveraged and how future work on additional sign languages could profit from building on existing sign language wordnet data. The results of our work are made publicly available.} } @inproceedings{borstell:22006:sign-lang:lrec, author = {B{\"o}rstell, Carl}, title = {Introducing the {signglossR} Package}, pages = {16--23}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22006.html}, doi = {10.63317/3sn6yhy5b23m}, abstract = {The signglossR package is a library written in the programming language R, intended as an easy-to-use resource for those who work with signed language data and are familiar with R. The package contains a variety of functions designed specifically towards signed language research, facilitating a single-pipeline workflow with R when accessing public language resources remotely (online) or a user's own files and data. The package specifically targets processing of image and video files, but also features some interaction with software commonly used by researchers working on signed language and gesture, such as ELAN and OpenPose. The signglossR package combines features and functionality from many other libraries and tools in order to simplify and collect existing resources in one place, as well as adding some new functionality, and adapt everything to the needs of researchers working with visual language data. In this paper, the main features of this package are introduced.} } @inproceedings{brosens:22002:sign-lang:lrec, author = {Brosens, Caro and Janssens, Margot and Verstraete, Sam and Vandamme, Thijs and De Durpel, Hannes}, title = {Moving towards a Functional Approach in the {Flemish} {Sign} {Language} Dictionary Making Process}, pages = {24--28}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22002.html}, doi = {10.63317/2ghrn4ddaur5}, abstract = {This presentation will outline the dictionary making process of the new online Flemish Sign Language dictionary launched in 2019. First some necessary background information is provided, consisting of a brief history of Flemish Sign Language (VGT) lexicography. Then three phases in the development of the renewed dictionary of VGT will be explored: (i) user research, (ii) data-cleaning and modeling, and (iii) innovations. More than wanting to project a report of lexicographic research on a website, the goal was to make the new dictionary a practical, user-friendly reference tool that meets the needs, expectations, and skills of the dictionary users. To gain a better understanding of who the users were, several sources were consulted: the user research by Joni Oyserman (2013), the quantitative data from Google Analytics and VGTC's own user profiles. Since 2017, VGTC has been using Signbank, an electronic database specifically developed to compile and manage lexicographic data for sign languages. Bringing together all this raw data inadvertently led to inconsistencies and small mistakes, therefore the data had to be manually revised and complemented. The VGT dictionary was mainly formally modernized, but there are also several substantive differences regarding the previous dictionary: for instance, search options were expanded, and semantic categories were added as well as a new feedback feature. In addition, the new website is also structurally different, it is now responsive to all screen sizes. Lastly, possible future innovations will briefly be discussed. VGTC aims to continuously improve both the user-based interface and the content of the current dictionary. Future goals include, but are not limited to, adding definitions and sample sentences (preferably extracted from the corpus), as well as information on the etymology and common use of signs.} } @inproceedings{chizhikova:22011:sign-lang:lrec, author = {Chizhikova, Anastasia and Kimmelman, Vadim}, title = {Phonetics of Negative Headshake in {Russian} {Sign} {Language}: A Small-Scale Corpus Study}, pages = {29--36}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22011.html}, doi = {10.63317/4or4xpdu7mbk}, abstract = {We analyzed negative headshake found in the online corpus of Russian Sign Language. We found that negative headshake can co-occur with negative manual signs, although most of these signs are not accompanied by it. We applied OpenFace, a Computer Vision toolkit, to extract head rotation measurements from video recordings, and analyzed the headshake in terms of the number of peaks (turns), the amplitude of the turns, and their frequency. We find that such basic phonetic measurements of headshake can be extracted using a combination of manual annotation and Computer Vision, and can be further used in comparative research across constructions and sign languages.} } @inproceedings{choubsaz:22003:sign-lang:lrec, author = {Choubsaz, Yassaman and Crasborn, Onno and Siyavoshi, Sara and Soleimanbeigi, Farzaneh}, title = {Documenting the Use of {Iranian} {Sign} {Language} ({ZEI}) in Kermanshah}, pages = {37--41}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22003.html}, doi = {10.63317/477qebssmjcs}, abstract = {We describe a sign language documentation project funded by the Endangered Languages Documentation Project (ELDP) in the province of Kermanshah, a city in west of Iran. The deposit at ELDP archive (elararchive.org) includes recording of 38 native signers of Zaban Eshareh Irani living in Kermanshah. The recordings start with an elicitation of the signs of the Farsi alphabet along with fingerspelling of some words as well as vocabulary elicitation of some basic concepts. Subsequently, the participants are asked to watch short movies and then they are asked to retell the story. Later, the participants have natural conversations in pairs guided by a deaf moderator. Initial annotations of ID-glosses and translations to Persian and English were also archived. ID-glosses are stored as a dataset in Global Signbank, along with a citation form of signs and their phonological description. The resulting datasets and one-hour annotation of the conversations are available to other researchers in ELDP archive.} } @inproceedings{danet:22023:sign-lang:lrec, author = {Danet, Claire and Thomas, Chlo{\'e} and Contesse, Adrien and R{\'e}bulard, Morgane and Bianchini, Claudia S. and Chevrefils, L{\'e}a and Doan, Patrick}, title = {Applying the Transcription System {Typannot} to Mouth Gestures}, pages = {42--47}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22023.html}, doi = {10.63317/2mp8y9eeyk7q}, abstract = {Research on sign languages (SLs) requires dedicated, efficient and comprehensive transcription systems to analyze and compare the sign parameters; at present, many transcription systems focus on manual parameters, relegating the non‐manual component to a lesser role. This article presents Typannot, a formal transcription system, and in particular its application to mouth gestures: 1) first, exposing its kinesiological approach, i.e. an intrinsic articulatory description anchored in the body; 2) then, showing its conception to integrate linguistic, graphic and technical aspects within a typeface; 3) finally, presenting its application to a corpus in French Sign Language (LSF) recorded with motion capture.} } @inproceedings{quadros:22022:sign-lang:lrec, author = {Quadros, Ronice M{\"u}ller de and Krusser, Renata and Saito, Daniela}, title = {{Libras} {Portal}: A Way of Documentation, a Way of Sharing}, pages = {48--52}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22022.html}, doi = {10.63317/5e5d8cs7ma55}, abstract = {Libras Portal is an interface that makes available in one single site a series of elements and tools related to the Brazilian Sign Language (Libras) and comprises Libras documentation which may be employed for research and for educational aims. Libras Portal was developed to codify tools that prop an education network and practice community, making possible the sharing of knowledge, data, and interaction in Libras and Portuguese. It involves accessibility and usability of the web, especially videos in Libras. The latter are access-friendly to available hyperlinks and tools related to communication with the target practice community. The layout also employs visual and textual resources for deaf users. The portal makes available resources for research and the teaching of language, namely Libras Grammar, Libras corpus, Sign Bank, and Literary Anthology of Libras. It is also a store for the sharing of literary, academic, and didactic materials, courses, glossaries, anthologies, lesson models, and grammar analyses. Consequently, tools were developed for the accessibility of deaf people, for easy web browsing, index information, video upload, research, and development of products for communities of deaf people. The current paper will describe the development of research and resources for accessibility.} } @inproceedings{filhol:22009:sign-lang:lrec, author = {Filhol, Michael and McDonald, John C.}, title = {Representation and Synthesis of Geometric Relocations}, pages = {53--58}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22009.html}, doi = {10.63317/3itqun936kbs}, abstract = {One of the key features of signed discourse is the geometric placements of gestural units in signing space. Signers use the geometry of signing space to describe the placements and forms of objects and also use it to contrast participants or locales in a story. Depending on the specific functions of the placement in the discourse, features such as geometric precision, gaze redirection and timing will all differ. A signing avatar must capture these differences to sign such discourse naturally. This paper builds on prior work that animated geometric depictions to enable a signing avatar to more naturally use signing space for opposing participants and concepts in discourse. Building from a structured linguistic description of a signed newscast, they system automatically synthesizes animation that correctly utilizes signing space to lay out the opposing locales in the report. The efficacy of the approach is demonstrated through comparisons of the avatar's motion with the source signing.} } @inproceedings{hall:22004:sign-lang:lrec, author = {Hall, Kathleen Currie and Aonuki, Yurika and Vesik, Kaili and Poy, April and Tolmie, Nico}, title = {Sign Language Phonetic Annotator-Analyzer: Open-Source Software for Form-Based Analysis of Sign Languages}, pages = {59--66}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22004.html}, doi = {10.63317/5fwe9vqy7eyx}, abstract = {This paper provides an introduction to the Sign Language Phonetic Annotator-Analyzer (SLP-AA) software, a free and open-source tool currently under development, for facilitating detailed form-based transcription of signs. The software is designed to have a user-friendly interface that allows coders to transcribe a great deal of phonetic detail without being constrained to a particular phonetic annotation system or phonological framework. Here, we focus on the `annotator' component of the software, outlining the functionality for transcribing movement, location, hand configuration, orientation, and contact, as well as the timing relations between them.} } @inproceedings{hassan:22008:sign-lang:lrec, author = {Hassan, Saad and Seita, Matthew and Berke, Larwan and Tian, Yingli and Gale, Elaine and Lee, Sooyeon and Huenerfauth, Matt}, title = {{ASL-Homework-RGBD} Dataset: An Annotated Dataset of 45 Fluent and Non-fluent Signers Performing {American} {Sign} {Language} Homeworks}, pages = {67--72}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22008.html}, doi = {10.63317/5curu82xqadx}, abstract = {We are releasing a dataset containing videos of both fluent and non-fluent signers using American Sign Language (ASL), which were collected using a Kinect v2 sensor. This dataset was collected as a part of a project to develop and evaluate computer vision algorithms to support new technologies for automatic detection of ASL fluency attributes. A total of 45 fluent and non-fluent participants were asked to perform signing homework assignments that are similar to the assignments used in introductory or intermediate level ASL courses. The data is annotated to identify several aspects of signing including grammatical features and non-manual markers. Sign language recognition is currently very data-driven and this dataset can support the design of recognition technologies, especially technologies that can benefit ASL learners. This dataset might also be interesting to ASL education researchers who want to contrast fluent and non-fluent signing.} } @inproceedings{isard:22034:sign-lang:lrec, author = {Isard, Amy and Konrad, Reiner}, title = {{MY} {DGS} -- {ANNIS}: {ANNIS} and the {Public} {DGS} {Corpus}}, pages = {73--79}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22034.html}, doi = {10.63317/3ogn2vzfyphg}, abstract = {In 2018 the DGS-Korpus project published the first full release of the Public DGS Corpus. The data have already been published in two different ways to fulfil the needs of different user groups, and we have now published the third portal MY DGS -- ANNIS using the ANNIS browser-based corpus software. ANNIS is a corpus query tool for visualization and querying of multi-layer corpus data. It has its own query language, AQL, and is accessed from a web browser without requiring a login. It allows more complex queries and visualizations than those provided by the existing research portal. We introduce ANNIS and its query language AQL, describe the structure of MY DGS -- ANNIS, and give some example queries. The use cases with queries over multiple annotation tiers and metadata illustrate the research potential of this powerful tool and show how students and researchers can explore the Public DGS Corpus.} } @inproceedings{jahn:22035:sign-lang:lrec, author = {Jahn, Elena and Khan, Calvin and Herrmann, Annika}, title = {Outreach and Science Communication in the {DGS-Korpus} Project: Accessibility of Data and the Benefit of Interactive Exchange between Communities}, pages = {80--87}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22035.html}, doi = {10.63317/3h8br8qvxixg}, abstract = {In this paper, we tackle the issues of science communication and dissemination within a sign language corpus project with a focus on spreading accessible information and involving the D/deaf community on various levels. We will discuss successful examples, challenges, and limitations to public relations in such a project and particularly elaborate on use cases. The focus group is presented as a best-practice example of a what we think is a necessary perspective: taking external knowledge seriously and let community experts interact with and provide feedback on a par with academic personnel. Showing both social media and on-site events, we present some exemplary approaches from our team involved in public relations.} } @inproceedings{jedlicka:22039:sign-lang:lrec, author = {Jedli{\v c}ka, Pavel and Kr{\v n}oul, Zden{\v e}k and {\v Z}elezn{\'y}, Milo{\v s} and M{\"u}ller, Lud{\v e}k}, title = {{MC-TRISLAN}: A Large {3D} Motion Capture Sign Language Data-set}, pages = {88--93}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22039.html}, doi = {10.63317/5pkibszgpvj9}, abstract = {The new 3D motion capture data corpus expands the portfolio of existing language resources by a corpus of 18~hours of Czech sign language. This helps to alleviate the current problem, which is a critical lack of high quality data necessary for research and subsequent deployment of machine learning techniques in this area. We currently provide the largest collection of annotated sign language recordings acquired by state-of-the-art 3D human body recording technology for the successful future deployment in communication technologies, especially machine translation and sign language synthesis.} } @inproceedings{jui:22018:sign-lang:lrec, author = {Jui, Tonni Das and Bejarano, Gissella and Rivas, Pablo}, title = {A Machine Learning-based Segmentation Approach for Measuring Similarity between Sign Languages}, pages = {94--101}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22018.html}, doi = {10.63317/395me5245fw8}, abstract = {Due to the lack of more variate, native and continuous datasets, sign languages are low-resources languages that can benefit from multilingualism in machine translation. In order to analyze the benefits of approaches like multilingualism, finding the similarity between sign languages can guide better matches and contributions between languages. However, calculating the similarity between sign languages again implies a laborious work to measure how close or distant signs are and their respective contexts. For that reason, we propose to support the similarity measurement between sign languages through a video-segmentation-based machine learning model that will quantify this match among signs of different countries' sign languages. Using a machine learning approach the similarity measurement process can run more smoothly, compared to a more manual approach. We use a pre-trained temporal segmentation model for British Sign Language (BSL). We test it on three datasets, an American Sign Language (ASL) dataset, an Indian Sign Language (ISL), and an Australian Sign Language (AUSLAN) dataset. We hypothesize that the percentage of segmented and recognized signs by this machine learning model can represent the percentage of overlap or similarity between British and the other three sign languages. In our ongoing work, we evaluate three metrics considering Swadesh's and Woodward's list and their synonyms. We found that our intermediate-strict metric coincides with a more classical analysis of the similarity between British and American Sign Language, as well as with the classical low measurement between Indian and British sign languages. On the other hand, our similarity measurement between British and Australian Sign language just holds for part of the Australian Sign Language and not the whole data sample.} } @inproceedings{kopf:22025:sign-lang:lrec, author = {Kopf, Maria and Schulder, Marc and Hanke, Thomas}, title = {The {Sign} {Language} {Dataset} {Compendium}: Creating an Overview of Digital Linguistic Resources}, pages = {102--109}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22025.html}, doi = {10.63317/4zuvsh66q97j}, abstract = {One of the challenges that sign language researchers face is the identification of suitable language datasets, particularly for cross-lingual studies. There is no single source of information on what sign language corpora and lexical resources exist or how they compare. Instead, they have to be found through extensive literature review or word-of-mouth. The amount of information available on individual datasets can also vary widely and may be distributed across different publications, data repositories and (potentially defunct) project websites. This article introduces the Sign Language Dataset Compendium, an extensive overview of linguistic resources for sign languages. It covers existing corpora and lexical resources, as well as commonly used data collection tasks. Special attention is paid to covering resources for many different languages from around the globe. All information is provided in a standardised format to make entries comparable, but kept flexible enough to allow for differences in content. The compendium is intended as a growing resource that will be updated regularly.} } @inproceedings{kuder:22020:sign-lang:lrec, author = {Kuder, Anna}, title = {Making Sign Language Corpora Comparable: A Study of Palm-Up and Throw-Away in {Polish} {Sign} {Language}, {German} {Sign} {Language}, and {Russian} {Sign} {Language}}, pages = {110--117}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22020.html}, doi = {10.63317/5p5r6rnjxe45}, abstract = {This paper is primarily devoted to describing the preparation phase of a large-scale comparative study based on naturalistic linguistic data drawn from multiple sign language corpora. To provide an example, I am using my current project on manual gestural elements in Polish Sign Language, German Sign Language, and Russian Sign Language. The paper starts with a description of the reasons behind undertaking this project. Then, I describe the scope of my study, which is focused on two manual elements present in all three mentioned sign languages: palm-up and throw-away; and the three corpora which are my data sources. This is followed by a presentation of the steps taken in the initial stages of the project in order to make the data comparable. Those steps are: choosing the adequate data samples from all three corpora, gathering all data within the chosen software, and creating an annotation schema that builds on the annotations already present in all three corpora. Even though the project is still underway, and the annotation process is ongoing, preliminary discussions about the nature of the analysed manual activities are presented based on the initial annotations for the sake of evaluating the created annotation schema. I conclude the paper with some remarks about the performance of the employed methodology.} } @inproceedings{kuder:22010:sign-lang:lrec, author = {Kuder, Anna and W{\'o}jcicka, Joanna and Mostowski, Piotr and Rutkowski, Pawe{\l}}, title = {Open Repository of the {Polish} {Sign} {Language} {Corpus}: Publication Project of the {Polish} {Sign} {Language} {Corpus}}, pages = {118--123}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22010.html}, doi = {10.63317/2s2bg4hax2r4}, abstract = {Between 2010 and 2020, the research team of the Section for Sign Linguistics collected, annotated, and translated a large corpus of Polish Sign Language (polski j{\k e}zyk migowy, PJM). After this task was finished, a substantial part of the gathered materials was published online as the Open Repository of the Polish Sign Language Corpus. The current paper gives an overview of the process of converting the material from the Corpus into the Repository. If presents and explains the decisions made along the way and describes the process of data preparation and publication. There are two levels of access to the Repository, which are meant to fulfil the needs of a wide range of public users, from members of the Deaf community, through hearing students of PJM, sign language teachers and interpreters, to users with academic background. We describe how corpus material available in open access was prepared to be searchable by text type and elicitation tasks, by sociolinguistic metadata, and by translation into written Polish. We go on to explain how access for research purposes differs from open access. We present possible ways in which data gathered in the Repository may be used by members of the signing community in Poland and abroad.} } @inproceedings{kuznetsova:22024:sign-lang:lrec, author = {Kuznetsova, Anna and Imashev, Alfarabi and Mukushev, Medet and Sandygulova, Anara and Kimmelman, Vadim}, title = {Functional Data Analysis of Non-manual Marking of Questions in {Kazakh-Russian} {Sign} {Language}}, pages = {124--131}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22024.html}, doi = {10.63317/3wxdh9h6k4jz}, abstract = {This paper is a continuation of Kuznetsova et al. (2021), which described non-manual markers of polar and wh-questions in comparison with statements in an NLP dataset of Kazakh-Russian Sign Language (KRSL) using Computer Vision. One of the limitations of the previous work was the distortion of the 3D face landmarks when the head was rotated. The proposed solution was to train a simple linear regression model to predict the distortion and then subtract it from the original output. We improve this technique with a multilayer perceptron. Another limitation that we intend to address in this paper is the discrete analysis of the continuous movement of non-manuals. In Kuznetsova et al. (2021) we averaged the value of the non-manual over its scope for statistical analysis. To preserve information on the shape of the movement, in this study we use a statistical tool that is often used in speech research, Functional Data Analysis, specifically Functional PCA.} } @inproceedings{martinod:22014:sign-lang:lrec, author = {Martinod, Emmanuella and Danet, Claire and Filhol, Michael}, title = {Two New {AZee} Production Rules Refining Multiplicity in {French} {Sign} {Language}}, pages = {132--138}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22014.html}, doi = {10.63317/3qkijow3hv46}, abstract = {This paper is a contribution to sign language (SL) modeling. We focus on the hitherto imprecise notion of "Multiplicity", assumed to express plurality in French Sign Language (LSF), using AZee approach. AZee is a linguistic and formal approach to modeling LSF. It takes into account the linguistic properties and specificities of LSF while respecting constraints linked to a modeling process. We present the methodology to extract AZee production rules. Based on the analysis of strong form-meaning associations in SL data (elicited image descriptions and short news), we identified two production rules structuring the expression of multiplicity in LSF. We explain how these newly extracted production rules are different from existing ones. Our goal is to refine the AZee approach to allow the coverage of a growing part of LSF. This work could lead to an improvement in SL synthesis and SL automatic translation.} } @inproceedings{moiselle:22016:sign-lang:lrec, author = {Moiselle, Rachel Ann and Leeson, Lorraine}, title = {Language Planning in Action: Depiction as a Driver of New Terminology in {Irish} {Sign} {Language}}, pages = {139--143}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22016.html}, doi = {10.63317/27qkg5zpm9u7}, abstract = {In this paper, we examine the linguistic phenomenon known as `depiction', which relates to the ability to visually represent semantic components (Dudis, 2004). While some elements of this have been described for Irish Sign Language, with particular attention to the `productive lexicon' (Leeson {\&} Grehan, 2004; Leeson {\&} Saeed, 2012; Matthews, 1996; O'Baoill {\&} Matthews, 2000), here, we take the analysis further, drawing on what we have learned from cognitive linguistics over the past decade. Drawing on several recently developed domain-specific glossaries (e.g., STEM1, Covid-192, political domain, Sexual, Domestic and Gender Based Violence (SDGBV)-related vocabulary) we present ongoing analysis indicating that a deliberate focus on iconicity, in particular, elements of depiction, appears to be a primary driver. We also consider the potential implications of the insights we intend to gain from Deaf-led glossary glossary development work in the context of Machine Translation goals, for example, for work in progress on the Horizon 2020 funded SignON project.} } @inproceedings{morgan:22026:sign-lang:lrec, author = {Morgan, Hope E. and Crasborn, Onno and Kopf, Maria and Schulder, Marc and Hanke, Thomas}, title = {Facilitating the Spread of New Sign Language Technologies across {Europe}}, pages = {144--147}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22026.html}, doi = {10.63317/4ukuahoyubkm}, abstract = {For developing sign language technologies like automatic translation, huge amounts of training data are required. Even the larger corpora available for some sign languages are tiny compared to the amounts of data used for corresponding spoken language technologies. The overarching goal of the European project EASIER is to develop a framework for bidirectional automatic translation between sign and spoken languages and between sign languages. One part of this multi-dimensional project is that it will pool available language resources from European sign languages into a larger dataset to address the data scarcity problem. This approach promises to open the floor for lower-resourced sign languages in Europe. This article focusses on efforts in the EASIER project to allow for new languages to make use of such technologies in the future. What are the characteristics of sign language resources needed to train recognition, translation, and synthesis algorithms, and how can other countries including those without any sign resources follow along with these developments? The efforts undertaken in EASIER include creating workflow documents and organizing training sessions in online workshops. They reflect the current state of the art, and will likely need to be updated in the coming decade.} } @inproceedings{morgan:22019:sign-lang:lrec, author = {Morgan, Hope E. and Sandler, Wendy and Stamp, Rose and Novogrodsky, Rama}, title = {{ISL-LEX} v.1: An Online Lexical Resource of {Israeli} {Sign} {Language}}, pages = {148--153}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22019.html}, doi = {10.63317/2eo6n47j4gbz}, abstract = {This paper describes a new online lexical resource and interactive tool for Israeli Sign Language, ISL-LEX v.1. The dataset contains 961 non-compound ISL signs with the following information: subjective frequency ratings from native signers, iconicity ratings from native and non-native signers (presented separately), and phonological properties in six domains. The selection of signs was also designed to reflect a broad distinction between those signs acquired early in childhood and those acquired later. ISL-LEX is an online interface built using the SIGN-LEX visualization (Caselli et al. 2022), and is intended for use by researchers, educators, and students. It is therefore offered in two text-based versions, English and Hebrew, with video instructions in ISL.} } @inproceedings{mukushev:22031:sign-lang:lrec, author = {Mukushev, Medet and Kydyrbekova, Aigerim and Kimmelman, Vadim and Sandygulova, Anara}, title = {Towards Large Vocabulary {Kazakh-Russian} {Sign} {Language} Dataset: {KRSL-OnlineSchool}}, pages = {154--158}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22031.html}, doi = {10.63317/4oixy3psku2p}, abstract = {This paper presents a new dataset for Kazakh-Russian Sign Language (KRSL) created for the purposes of Sign Language Processing. In 2020, Kazakhstan's schools were quickly switched to online mode due to the COVID-19 pandemic. Every working day, the El-arna TV channel was broadcasting video lessons for grades from 1 to 11 with sign language translation. This opportunity allowed us to record a corpus with a large vocabulary and spontaneous SL interpretation. To this end, this corpus contains video recordings of Kazakhstan's online school translated to Kazakh-Russian sign language by 7 interpreters. At the moment we collected and cleaned 890 hours of video material. A custom annotation tool was created to make the process of data annotation simple and easy-to-use by the Deaf community. To date, around 325 hours of videos have been annotated with glosses and 4,009 lessons out of 4,547 were transcribed with automatic speech-to-text software. The KRSL-OnlineSchool dataset will be made publicly available at https://krslproject.github.io/online-school/} } @inproceedings{mukushev:22030:sign-lang:lrec, author = {Mukushev, Medet and Sabyrov, Arman and Sultanova, Madina and Kimmelman, Vadim and Sandygulova, Anara}, title = {Towards Semi-automatic Sign Language Annotation Tool: {SLAN-tool}}, pages = {159--164}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22030.html}, doi = {10.63317/2tgdrajbv458}, abstract = {This paper presents a semi-automatic annotation tool for sign languages namely SLAN-tool. The SLAN-tool provides a web-based service for the annotation of sign language videos. Researchers can use the SLAN-tool web service to annotate new and existing sign language datasets with different types of annotations, such as gloss, handshape configurations, and signing regions. This is allowed using a custom tier adding functionality. A unique feature of the tool is its automatic annotation functionality which uses several neural network models in order to recognize signing segments from videos and classify handshapes according to HamNoSys handshape inventory. Furthermore, SLAN-tool users can export annotations and import them into ELAN. The SLAN-tool is publicly available at https://slan-tool.com.} } @inproceedings{neidle:22037:sign-lang:lrec, author = {Neidle, Carol and Opoku, Augustine and Ballard, Carey M. and Dafnis, Konstantinos M. and Chroni, Evgenia and Metaxas, Dimitris}, title = {Resources for Computer-Based Sign Recognition from Video, and the Criticality of Consistency of Gloss Labeling across Multiple Large {ASL} Video Corpora}, pages = {165--172}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22037.html}, doi = {10.63317/35seq7bny696}, abstract = {The WLASL purports to be ``the largest video dataset for Word-Level American Sign Language (ASL) recognition.'' It brings together various publicly shared video collections that could be quite valuable for sign recognition research, and it has been used extensively for such research. However, a critical problem with the accompanying annotations has heretofore not been recognized by the authors, nor by those who have exploited these data: There is no 1-1 correspondence between sign productions and gloss labels. Here we describe a large (and recently expanded and enhanced), linguistically annotated, downloadable, video corpus of citation-form ASL signs shared by the American Sign Language Linguistic Research Project (ASLLRP)---with 23,452 sign tokens and an online Sign Bank---in which such correspondences are enforced. We furthermore provide annotations for 19,672 of the WLASL video examples consistent with ASLLRP glossing conventions. For those wishing to use WLASL videos, this provides a set of annotations that makes it possible: (1) to use those data reliably for computational research; and/or (2) to combine the WLASL and ASLLRP datasets, creating a combined resource that is larger and richer than either of those datasets individually, with consistent gloss labeling for all signs. We also offer a summary of our own sign recognition research to date that exploits these data resources.} } @inproceedings{power:22021:sign-lang:lrec, author = {Power, Justin M. and Quinto-Pozos, David and Law, Danny}, title = {Signed Language Transcription and the Creation of a Cross-linguistic Comparative Database}, pages = {173--180}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22021.html}, doi = {10.63317/3in4sm54czhy}, abstract = {As the availability of signed language data has rapidly increased, sign scholars have been confronted with the challenge of creating a common framework for the cross-linguistic comparison of the phonological forms of signs. While transcription techniques have played a fundamental role in the creation of cross-linguistic comparative databases for spoken languages, transcription has featured much less prominently in sign research and lexicography. Here we report the experiences of the Sign Change project in using the signed language transcription system HamNoSys to create a comparative database of basic vocabulary for thirteen signed languages. We report the results of a small-scale study, in which we measured (i) the average time required for two trained transcribers to complete a transcription and (ii) the similarity of their independently produced transcriptions. We find that, across the two transcribers, the transcription of one sign required, on average, one minute and a half. We also find that the similarity of transcriptions differed across phonological parameters. We consider the implications of our findings about transcription time and transcription similarity for other projects that plan to incorporate transcription techniques.} } @inproceedings{smith:22017:sign-lang:lrec, author = {Smith, River Tae and Willoughby, Louisa and Johnston, Trevor}, title = {Integrating {Auslan} Resources into the Language Data Commons of {Australia}}, pages = {181--186}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22017.html}, doi = {10.63317/3n8jyropzpue}, abstract = {This paper describes a project to secure Auslan (Australian Sign Language) resources within a national language data network called the Language Data Commons of Australia (LDaCA). The resources are Auslan Signbank, a web-based multi-media dictionary, and the Auslan Corpus, a collection of video recordings of the language being used in various contexts with time-aligned ELAN annotation files. We aim to make these resources accessible to the language community, encourage community participation in the curation of the data, and facilitate and extend their uses in language teaching and linguistic research. The software platforms of both resources will be made compatible with other LDaCA resources; and the two will also be aggregated and linked so that (i) users of the dictionary can view attested corpus examples for an entry; and (ii) users of the corpus can instantly view the dictionary entry for an already glossed sign to check phonological, lexical and grammatical information about it, and/or to ensure that the correct annotation gloss (aka `ID-gloss') for a sign token has been chosen. This will enhance additions to annotations in the Auslan Corpus, entries in Auslan Signbank and the integrity of research based on both.} } @inproceedings{stamp:22012:sign-lang:lrec, author = {Stamp, Rose and Khatib, Lilyana and Hel-Or, Hagit}, title = {Capturing Distalization}, pages = {187--191}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22012.html}, doi = {10.63317/3oiyuhqoznzi}, abstract = {Coding and analyzing large amounts of video data is a challenge for sign language researchers, who traditionally code 2D video data manually. In recent years, the implementation of 3D motion capture technology as a means of automatically tracking movement in sign language data has been an important step forward. Several studies show that motion capture technologies can measure sign language movement parameters -- such as volume, speed, variance -- with high accuracy and objectivity. In this paper, using motion capture technology and machine learning, we attempt to automatically measure a more complex feature in sign language known as distalization. In general, distalized signs use the joints further from the torso (such as the wrist), however, the measure is relative and therefore distalization is not straightforward to measure. The development of a reliable and automatic measure of distalization using motion tracking technology is of special interest in many fields of sign language research.} } @inproceedings{stamp:22015:sign-lang:lrec, author = {Stamp, Rose and Ohanin, Ora and Lanesman, Sara}, title = {The {Corpus} of {Israeli} {Sign} {Language}}, pages = {192--197}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22015.html}, doi = {10.63317/3fcmybonnp6z}, abstract = {The Corpus of Israeli Sign Language is a four-year project (2020-2024) which aims to create a digital open-access corpus of spontaneous and elicited data from a representative sample of the Israeli deaf community. In this paper, the methodology for building the Corpus of Israeli Sign Language is described. Israeli Sign Language (ISL) is the main sign language used across Israel by around 10,000 people. As part of the corpus, data will be collected from 120 deaf ISL signers across four sites in Israel: Tel Aviv and the Centre, Haifa and the North, Be'er Sheva and the South and Jerusalem and the surrounding area. Participants will engage in a variety of tasks, eliciting a range of signing styles from free conversation to lexical elicitation. The dataset will consist of recordings of over 360 hours of video data which will be used to conduct sociolinguistic investigations of language contact, variation, and change in the near term, and other linguistic analyses in the future.} } @inproceedings{woll:22007:sign-lang:lrec, author = {Woll, Bencie and Fox, Neil and Cormier, Kearsy}, title = {Segmentation of Signs for Research Purposes: Comparing Humans and Machines}, pages = {198--201}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22007.html}, doi = {10.63317/2ujma5nbrbyc}, abstract = {Sign languages such as British Sign Language (BSL) are visual languages which lack standard writing systems. Annotation of sign language data, especially for the purposes of machine readability, is therefore extremely slow. Tools to help automate and thus speed up the annotation process are very much needed. Here we test the development of one such tool (VIA-SLA), which uses temporal convolutional networks (Renz et al., 2021a, b) for the purpose of segmenting continuous signing in any sign language, and is designed to integrate smoothly with ELAN, the widely used annotation software for analysis of videos of sign language. We compare automatic segmentation by machine with segmentation done by a human, both in terms of time needed and accuracy of segmentation, using samples taken from the BSL Corpus (Schembri et al., 2014). A small sample of four short video files is tested (mean duration 25 seconds). We find that mean accuracy in terms of number and location of segmentations is relatively high, at around 78{\%}. This preliminary test suggests that VIA-SLA promises to be very useful for sign linguists.} } @inproceedings{xia:22038:sign-lang:lrec, author = {Xia, Zhaoyang and Chen, Yuxiao and Zhangli, Qilong and Huenerfauth, Matt and Neidle, Carol and Metaxas, Dimitris}, title = {Sign Language Video Anonymization}, pages = {202--211}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22038.html}, doi = {10.63317/2putrcawtrrh}, abstract = {Deaf signers who wish to communicate in their native language frequently share videos on the Web. However, videos cannot preserve privacy---as is often desirable for discussion of sensitive topics---since both hands and face convey critical linguistic information and therefore cannot be obscured without degrading communication. Deaf signers have expressed interest in video anonymization that would preserve linguistic content. However, attempts to develop such technology have thus far shown limited success. We are developing a new method for such anonymization, with input from ASL signers. We modify a motion-based image animation model to generate high-resolution videos with the signer identity changed, but with the preservation of linguistically significant motions and facial expressions. An asymmetric encoder-decoder structured image generator is used to generate the high-resolution target frame from the low-resolution source frame based on the optical flow and confidence map. We explicitly guide the model to attain a clear generation of hands and faces by using bounding boxes to improve the loss computation. FID and KID scores are used for the evaluation of the realism of the generated frames. This technology shows great potential for practical applications to benefit deaf signers.} } @proceedings{lrec:sign-lang:20, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, title = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, url = {https://lrec2020.lrec-conf.org/media/proceedings/Workshops/Books/SIGN2020book.pdf}, doi = {10.63317/3nocn9xntuki} } @inproceedings{becker:20039:sign-lang:lrec, author = {Becker, Amelia and Catt, Donovan H. and Hochgesang, Julie A.}, title = {Back and Forth between Theory and Application: Shared Phonological Coding Between {ASL} {Signbank} and {ASL-LEX}}, pages = {1--6}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20039.html}, doi = {10.63317/4m3uqsd76fu4}, abstract = {The development of signed language lexical databases, digital organizations that describe different phonological features of and attempt to establish relationships between signs has resulted in a renewed interest in the phonological descriptions used to uniquely identify and organize the lexicons of respective sign languages (van der Kooij, 2002; Fenlon et al., 2016; Brentari et al., 2018). Throughout the mutually shared coding process involved in organizing two lexical databases, ASL Signbank (Hochgesang, Crasborn and Lillo-Martin, 2020) and ASL-LEX (Caselli et al., 2016), issues have arisen that require revisiting how phonological features and categories are to be applied and even decided upon, and which would adequately distinguish lexical contrast for respective sign languages. The paper concludes by exploring the inverse of the theory-to-database relationship. Examples are given of theoretical implications and research questions that arise from consequences of language resource building. These are presented as evidence that not only does theory impact organization of databases but that the process of database creation can also inform our theories.} } @inproceedings{belissen:20028:sign-lang:lrec, author = {Belissen, Valentin and Gouiff{\`e}s, Mich{\`e}le and Braffort, Annelies}, title = {Improving and Extending Continuous Sign Language Recognition: Taking Iconicity and Spatial Language into Account}, pages = {7--12}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20028.html}, doi = {10.63317/3ag3ew9hmg3x}, abstract = {In a lot of recent research, attention has been drawn to recognizing sequences of lexical signs in continuous Sign Language corpora, often artificial. However, as SLs are structured through the use of space and iconicity, focusing on lexicon only prevents the field of Continuous Sign Language Recognition (CSLR) from extending to Sign Language Understanding and Translation. \par In this article, we propose a new formulation of the CSLR problem and discuss the possibility of recognizing higher-level linguistic structures in SL videos, like classifier constructions. These structures show much more variability than lexical signs, and are fundamentally different than them in the sense that form and meaning can not be disentangled. Building on the recently published French Sign Language corpus Dicta-Sign-LSF-v2, we discuss the performance and relevance of a simple recurrent neural network trained to recognize illustrative structures.} } @inproceedings{bono:20012:sign-lang:lrec, author = {Bono, Mayumi and Sakaida, Rui and Okada, Tomohiro and Miyao, Yusuke}, title = {Utterance-Unit Annotation for the {JSL} Dialogue Corpus: Toward a Multimodal Approach to Corpus Linguistics}, pages = {13--20}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20012.html}, doi = {10.63317/5jeu7q8niir2}, abstract = {This paper describes a method for annotating the Japanese Sign Language (JSL) dialogue corpus. We developed a way to identify interactional boundaries and define a `utterance unit' in sign language using various multimodal features accompanying signing. The utterance unit is an original concept for segmenting and annotating sign language dialogue referring to signer's native sense from the perspectives of Conversation Analysis (CA) and Interaction Studies. First of all, we postulated that we should identify a fundamental concept of interaction-specific unit for understanding interactional mechanisms, such as turn-taking (Sacks et al. 1974), in sign-language social interactions. Obviously, it does should not relying on a spoken language writing system for storing signings in corpora and making translations. We believe that there are two kinds of possible applications for utterance units: one is to develop corpus linguistics research for both signed and spoken corpora; the other is to build an informatics system that includes, but is not limited to, a machine translation system for sign languages.} } @inproceedings{borstell:20011:sign-lang:lrec, author = {B{\"o}rstell, Carl and Crasborn, Onno and Whynot, Lori}, title = {Measuring Lexical Similarity across Sign Languages in {Global} {Signbank}}, pages = {21--26}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20011.html}, doi = {10.63317/4fki3n6hmt3x}, abstract = {Lexicostatistics is the main method used in previous work measuring linguistic distances between sign languages. As a method, it disregards any possible structural/grammatical similarity, instead focusing exclusively on lexical items, but it is time consuming as it requires some comparable phonological coding (i.e. form description) as well as concept matching (i.e. meaning description) of signs across the sign languages to be compared. In this paper, we present a novel approach for measuring lexical similarity across any two sign languages using the Global Signbank platform, a lexical database of uniformly coded signs. The method involves a feature-by-feature comparison of all matched phonological features. This method can be used in two distinct ways: 1) automatically comparing the amount of lexical overlap between two sign languages (with a more detailed feature-description than previous lexicostatistical methods); 2) finding exact form-matches across languages that are either matched or mismatched in meaning (i.e. true or false friends). We show the feasability of this method by comparing three languages (datasets) in Global Signbank, and are currently expanding both the size of these three as well as the total number of datasets.} } @inproceedings{brumm:20020:sign-lang:lrec, author = {Brumm, Maren and Grigat, Rolf-Rainer}, title = {Optimised Preprocessing for Automatic Mouth Gesture Classification}, pages = {27--32}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20020.html}, doi = {10.63317/2nked8tg6wg9}, abstract = {Mouth gestures are facial expressions in sign language, that do not refer to lip patterns of a spoken language. Research on this topic has been limited so far. The aim of this work is to automatically classify mouth gestures from video material by training a neural network. This could render time-consuming manual annotation unnecessary and help advance the field of automatic sign language translation. However, it is a challenging task due to the little data available as training material and the similarity of different mouth gesture classes. In this paper we focus on the preprocessing of the data, such as finding the area of the face important for mouth gesture recognition. Furthermore we analyse the duration of mouth gestures and determine the optimal length of video clips for classification. Our experiments show, that this can improve the classification results significantly and helps to reach a near human accuracy.} } @inproceedings{cabral:20024:sign-lang:lrec, author = {Cabral, Pedro and Gon{\c c}alves, Matilde and Nicolau, Hugo and Coheur, Lu{\'i}sa and Santos, Ruben}, title = {{PE2LGP} Animator: A Tool to Animate a {Portuguese} {Sign} {Language} Avatar}, pages = {33--38}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20024.html}, doi = {10.63317/5g9dymqkjaxe}, abstract = {Software for the production of sign languages is much less common than for spoken languages. Such software usually relies on 3D humanoid avatars to produce signs which, inevitably, necessitates the use of animation. One barrier to the use of popular animation tools is their complexity and steep learning curve, which can be hard to master for inexperienced users. Here, we present PE2LGP, an authoring system that features a 3D avatar that signs Portuguese Sign Language. Our Animator is designed specifically to craft sign language animations using a key frame method, and is meant to be easy to use and learn to users without animation skills. We conducted a preliminary evaluation of the Animator, where we animated seven Portuguese Sign Language sentences and asked four sign language users to evaluate their quality. This evaluation revealed that the system, in spite of its simplicity, is indeed capable of producing comprehensible messages.} } @inproceedings{cueto:20022:sign-lang:lrec, author = {Cueto, Mark and He, Winnie and Untiveros, Rei and Zu{\~n}iga, Josh and Rivera, Joanna Pauline}, title = {Translating an Aesop's Fable to {Filipino} {Sign} {Language} through {3D} Animation}, pages = {39--44}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20022.html}, doi = {10.63317/5gb6exfda2xi}, abstract = {According to the National Statistics Office (2003) in the 2000 Population Census, the deaf community in the Philippines numbered to about 121,000 deaf and hard of hearing Filipinos. Deaf and hard of hearing Filipinos in these communities use the Filipino Sign Language (FSL) as the main method of manual communication. Deaf and hard of hearing children experience difficulty in developing reading and writing skills through traditional methods of teaching used primarily for hearing children. This study aims to translate an Aesop's fable to Filipino Sign Language with the use of 3D animation resulting to a video output. The video created contains a 3D animated avatar performing the sign translations to FSL (mainly focusing on hand gestures which includes hand shape, palm orientation, location, and movement) on screen beside their English text equivalent and related images. The final output was then evaluated by FSL deaf signers. Evaluation results showed that the final output can potentially be used as a learning material. In order to make it more effective as a learning material, it is very important to consider the animation's appearance, speed, naturalness, and accuracy. In this paper, the common action units were also listed for easier construction of animations of the signs.} } @inproceedings{dociofernandez:20013:sign-lang:lrec, author = {Doc{\'i}o-Fern{\'a}ndez, Laura and Alba-Castro, Jos{\'e} Luis and Torres-Guijarro, Soledad and Rodr{\'i}guez-Banga, Eduardo and Rey-Area, Manuel and P{\'e}rez-P{\'e}rez, Ania and Rico-Alonso, Sonia and Garc{\'i}a-Mateo, Carmen}, title = {{LSE{\_}UVIGO}: A Multi-source Database for {Spanish} {Sign} {Language} Recognition}, pages = {45--52}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20013.html}, doi = {10.63317/3ryiv6hpp85t}, abstract = {This paper presents LSE{\_}UVIGO, a multi-source database designed to foster research on Sign Language Recognition. It is being recorded and compiled for Spanish Sign Language (LSE acronym in Spanish) and contains also spoken Galician language, so it is very well fitted to research on these languages, but also quite useful for fundamental research in any other sign language. LSE{\_}UVIGO is composed of two datasets: LSE{\_}Lex40{\_}UVIGO, a multi-sensor and multi-signer dataset acquired from scratch, designed as an incremental dataset, both in complexity of the visual content and in the variety of signers. It contains static and co-articulated sign recordings, fingerspelled and gloss-based isolated words, and sentences. Its acquisition is done in a controlled lab environment in order to obtain good quality videos with sharp video frames and RGB and depth information, making them suitable to try different approaches to automatic recognition. The second subset, LSE{\_}TVGWeather{\_}UVIGO is being populated from the regional television weather forecasts interpreted to LSE, as a faster way to acquire high quality, continuous LSE recordings with a domain-restricted vocabulary and with a correspondence to spoken sentences.} } @inproceedings{filhol:20009:sign-lang:lrec, author = {Filhol, Michael}, title = {Elicitation and Corpus of Spontaneous Sign Language Discourse Representation Diagrams}, pages = {53--60}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20009.html}, doi = {10.63317/5nrdo6ozrsdj}, abstract = {While Sign Languages have no standard written form, many signers do capture their language in some form of spontaneous graphical form. We list a few use cases (discourse preparation, deverbalising for translation, etc.) and give examples of diagrams. After hypothesising that they contain regular patterns of significant value, we propose to build a corpus of such productions. The main contribution of this paper is the specification of the elicitation protocol, explaining the variables that are likely to affect the diagrams collected. We conclude with a report on the current state of a collection following this protocol, and a few observations on the collected contents. A first prospect is the standardisation of a scheme to represent SL discourse in a way that would make them sharable. A subsequent longer-term prospect is for this scheme to be owned by users and with time be shaped into a script for their language.} } @inproceedings{filhol:20015:sign-lang:lrec, author = {Filhol, Michael and McDonald, John C.}, title = {The Synthesis of Complex Shape Deployments in Sign Language}, pages = {61--68}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20015.html}, doi = {10.63317/4rxzbmw8i78z}, abstract = {Proform constructs such as classifier predicates and size and shape specifiers are essential elements of Sign Language communication, but have remained a challenge for synthesis due to their highly variable nature. In contrast to frozen signs, which may be pre-animated or recorded, their variability necessitates a new approach both to their linguistic description and to their synthesis in animation. Though the specification and animation of classifier predicates was covered in previous works, size and shape specifiers have to this date remain unaddressed. This paper presents an efficient method for linguistically describing such specifiers using a small number of rules that cover a large range of possible constructs. It continues to show that with a small number of services in a signing avatar, these descriptions can be synthesized in a natural way that captures the essential gestural actions while also including the subtleties of human motion that make the signing legible.} } @inproceedings{fragkiadakis:20007:sign-lang:lrec, author = {Fragkiadakis, Manolis and Nyst, Victoria and van der Putten, Peter}, title = {Signing as Input for a Dictionary Query: Matching Signs Based on Joint Positions of the Dominant Hand}, pages = {69--74}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20007.html}, doi = {10.63317/2ngd5uiu5xup}, abstract = {This study presents a new methodology to search sign language lexica, using a full sign as input for a query. Thus, a dictionary user can look up information about a sign by signing the sign to a webcam. The recorded sign is then compared to potential matching signs in the lexicon. As such, it provides a new way of searching sign language dictionaries to complement existing methods based on (spoken language) glosses or phonological features, like handshape or location. The method utilizes OpenPose to extract the body and finger joint positions. Dynamic Time Warping (DTW) is used to quantify the variation of the trajectory of the dominant hand and the average trajectories of the fingers. Ten people with various degrees of sign language proficiency have participated in this study. Each subject viewed a set of 20 signs from the newly compiled Ghanaian sign language lexicon and was asked to replicate the signs. The results show that DTW can predict the matching sign with 87{\%} and 74{\%} accuracy at the Top-10 and Top-5 ranking level respectively by using only the trajectory of the dominant hand. Additionally, more proficient signers obtain 90{\%} accuracy at the Top-10 ranking. The methodology has the potential to be used also as a variation measurement tool to quantify the difference in signing between different signers or sign languages in general.} } @inproceedings{hanke:20016:sign-lang:lrec, author = {Hanke, Thomas and Schulder, Marc and Konrad, Reiner and Jahn, Elena}, title = {Extending the {Public} {DGS} {Corpus} in Size and Depth}, pages = {75--82}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20016.html}, doi = {10.63317/2ajntiuu3dxv}, abstract = {In 2018 the DGS-Korpus project published the first full release of the Public DGS Corpus. This event marked a change of focus for the project. While before most attention had been on increasing the size of the corpus, now an increase in its depth became the priority. New data formats were added, corpus annotation conventions were released and OpenPose pose information was published for all transcripts. The community and research portal websites of the corpus also received upgrades, including persistent identifiers, archival copies of previous releases and improvements to their usability on mobile devices.The research portal was enhanced even further, improving its transcript web viewer, adding a KWIC concordance view, introducing cross-references to other linguistic resources of DGS and making its entire interface available in German in addition to English. This article provides an overview of these changes, chronicling the evolution of the Public DGS Corpus from its first release in 2018, through its second release in 2019 until its third release in 2020.} } @inproceedings{hanke:20030:sign-lang:lrec, author = {Hanke, Thomas and Jahn, Elena and W{\"a}hl, Sabrina and B{\"o}se, Oliver and K{\"o}nig, Lutz}, title = {{SignHunter} -- A Sign Elicitation Tool Suitable for Deaf Events}, pages = {83--88}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20030.html}, doi = {10.63317/2s9zd465t94t}, abstract = {This paper presents SignHunter, a tool for collecting isolated signs, and discusses application possibilities. SignHunter is successfully used within the DGS-Korpus project to collect name signs for places and cities. The data adds to the content of a German Sign Language (DGS) -- German dictionary which is currently being developed, as well as a freely accessible subset of the DGS Corpus, the Public DGS Corpus. We discuss reasons to complement a natural language corpus by eliciting concepts without context and present an application example of SignHunter.} } @inproceedings{hassan:20034:sign-lang:lrec, author = {Hassan, Saad and Berke, Larwan and Vahdani, Elahe and Jing, Longlong and Tian, Yingli and Huenerfauth, Matt}, title = {An Isolated-Signing {RGBD} Dataset of 100 {American} {Sign} {Language} Signs Produced by Fluent {ASL} Signers}, pages = {89--94}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20034.html}, doi = {10.63317/29akwyczh4gc}, abstract = {We have collected a new dataset consisting of color and depth videos of fluent American Sign Language (ASL) signers performing sequences of 100 ASL signs from a Kinect v2 sensor. This directed dataset had originally been collected as part of an ongoing collaborative project, to aid in the development of a sign-recognition system for identifying occurrences of these 100 signs in video. The set of words consist of vocabulary items that would commonly be learned in a first-year ASL course offered at a university, although the specific set of signs selected for inclusion in the dataset had been motivated by project-related factors. Given increasing interest among sign-recognition and other computer-vision researchers in red-green-blue-depth (RBGD) video, we release this dataset for use by the research community. In addition to the RGB video files, we share depth and HD face data as well as additional features of face, hands, and body produced through post-processing of this data.} } @inproceedings{isard:20037:sign-lang:lrec, author = {Isard, Amy}, title = {Approaches to the Anonymisation of Sign Language Corpora}, pages = {95--100}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20037.html}, doi = {10.63317/5jfpyerz64od}, abstract = {In this paper we survey the state of the art for the anonymisation of sign language corpora. We begin by exploring the motivations behind anonymisation and the close connection with the issue of ethics and informed consent for corpus participants. We detail how the the names which should be anonymised can be identified. We then describe the processes which can be used to anonymise both the video and the annotations belonging to a corpus, and the variety of ways in which these can be carried out. We provide examples for all of these processes from three sign language corpora in which anonymisation of the data has been performed.} } @inproceedings{jedlicka:20027:sign-lang:lrec, author = {Jedli{\v c}ka, Pavel and Kr{\v n}oul, Zden{\v e}k and Kanis, Jakub and {\v Z}elezn{\'y}, Milo{\v s}}, title = {Sign Language Motion Capture Dataset for Data-driven Synthesis}, pages = {101--106}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20027.html}, doi = {10.63317/3r5dtqo9dknk}, abstract = {This paper presents a new 3D motion capture dataset of Czech Sign Language (CSE). Its main purpose is to provide the data for further analysis and data-based automatic synthesis of CSE utterances. The content of the data in the given limited domain of weather forecasts was carefully selected by the CSE linguists to provide the necessary utterances needed to produce any new weather forecast. The dataset was recorded using the state-of-the-art motion capture (MoCap) technology to provide the most precise trajectories of the motion. In general, MoCap is a device capable of accurate recording of motion directly in 3D space. The data contains trajectories of body, arms, hands and face markers recorded at once to provide consistent data without the need for the time alignment.} } @inproceedings{johnson:20019:sign-lang:lrec, author = {Johnson, Ronan and Wolfe, Rosalee}, title = {A survey of Shading Techniques for Facial Deformations on Sign Language Avatars}, pages = {107--112}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20019.html}, doi = {10.63317/52pbfwcyy5b5}, abstract = {Of the five phonemic parameters in sign language (handshape, location, palm orientation, movement and nonmanual expressions), the one that still poses the most challenges for effective avatar display is nonmanual signals. Facial nonmanual signals carry a rich combination of linguistic and pragmatic information, but current techniques have yet to portray these in a satisfactory manner. Due to the complexity of facial movements, additional considerations must be taken into account for rendering in real time. Of particular interest is the shading areas of facial deformations to improve legibility. In contrast to more physically-based, compute-intensive techniques that more closely mimic nature, we propose using a simple, classic, Phong illumination model with a dynamically modified layered texture. To localize and control the desired shading, we utilize an opacity channel within the texture. The new approach, when applied to our avatar ``Paula'', results in much quicker render times than more sophisticated, computationally intensive techniques.} } @inproceedings{kaczmarek:20021:sign-lang:lrec, author = {Kaczmarek, Marion and Filhol, Michael}, title = {Use cases for a Sign Language Concordancer}, pages = {113--116}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20021.html}, doi = {10.63317/4rjn9889r7sv}, abstract = {This article treats about a Sign Language concordancer. In the past years, the need for content translated into Sign Language has been growing, and is still growing nowadays. Yet, unlike their text-to-text counterparts, Sign Language translators are not equipped with computer-assisted translation software. As we aim to provide them with such software, we explore the possibilities offered by a first tool: a Sign Language concordancer. It includes designing an alignments database as well as a search function to browse it. Testing sessions with professionals highlight relevant use cases for their professional practices. It can either comfort the translator when the results are identical, or show the importance of context when the results are different for a same expression. This concordancer is available online, and aim to be a collaborative tool. Though our current database is small, we hope for translators to invest themselves and help us to keep it expanding.} } @inproceedings{kamal:20029:sign-lang:lrec, author = {Kamal, Zina and Hassani, Hossein}, title = {Towards {Kurdish} Text to Sign Translation}, pages = {117--122}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20029.html}, doi = {10.63317/39izdec47vq4}, abstract = {The resources and technologies for Sign language processing of resourceful languages are emerging, while the low-resource languages are falling behind. Kurdish is a multi-dialect language, and it is considered a low-resource language. It is spoken by approximately 30 million people in several countries, which denotes that it has a large community with hearing-impairments as well. This paper reports on a project which aims to develop the necessary data and tools to process the Sign language for Sorani as one of the spoken Kurdish dialects. We present the results of developing a dataset in HamNoSys and its corresponding SiGML form for the Kurdish Sign lexicon. We use this dataset to implement a sign-supported Kurdish tool to check the accuracy of the Sign lexicon. We tested the tool by presenting it to hearing-impaired individuals. The experiment showed that 100{\%} of the translated letters were understandable by a hearing-impaired person. The percentages were 65{\%} for isolated words, and approximately 30{\%} for the words in sentences. The data is publicly available at https://github.com/KurdishBLARK/KurdishSignLanguage for non-commercial use under the CC BY-NC-SA 4.0 licence} } @inproceedings{koulierakis:20035:sign-lang:lrec, author = {Koulierakis, Ioannis and Siolas, Georgios and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Stafylopatis, Andreas-Georgios}, title = {Recognition of Static Features in Sign Language Using Key-Points}, pages = {123--126}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20035.html}, doi = {10.63317/4a7uo3vu3832}, abstract = {In this paper we report on a research effort focusing on recognition of static features of sign formation in single sign videos. Three sequential models have been developed for handshape, palm orientation and location of sign formation respectively, which make use of key-points extracted via OpenPose software. The models have been applied to a Danish and a Greek Sign Language dataset, providing results around 96{\%}. Moreover, during the reported research, a method has been developed for identifying the time-frame of real signing in the video, which allows to ignore transition frames during sign recognition processing.} } @inproceedings{langer:20017:sign-lang:lrec, author = {Langer, Gabriele and Schulder, Marc}, title = {Collocations in Sign Language Lexicography: Towards Semantic Abstractions for Word Sense Discrimination}, pages = {127--134}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20017.html}, doi = {10.63317/44rgzd2hd9zs}, abstract = {In general monolingual lexicography a corpus-based approach to word sense discrimination (WSD) is the current standard. Automatically generated lexical profiles such as Word Sketches provide an overview on typical uses in the form of collocate lists grouped by their part of speech categories and their syntactic dependency relations to the base item. Collocates are sorted by their typicality according to frequency-based rankings. With the advancement of sign language (SL) corpora, SL lexicography can finally be based on actual language use as reflected in corpus data. In order to use such data effectively and gain new insights on sign usage, automatically generated collocation profiles need to be developed under the special conditions and circumstances of the SL data available. One of these conditions is that many of the prerequesites for the automatic syntactic parsing of corpora are not yet available for SL. In this article we describe a collocation summary generated from DGS Corpus data which is used for WSD as well as in entry-writing. The summary works based on the glosses used for lemmatisation. In addition, we explore how other resources can be utilised to add an additional layer of semantic grouping to the collocation analysis. For this experimental approach we use glosses, concepts, and wordnet supersenses.} } @inproceedings{liang:20031:sign-lang:lrec, author = {Liang, Xing and Woll, Bencie and Epaminondas, Kapetanios and Angelopoulou, Anastasia and Al-Batat, Reda}, title = {Machine Learning for Enhancing Dementia Screening in Ageing Deaf Signers of {British} {Sign} {Language}}, pages = {135--138}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20031.html}, doi = {10.63317/2sjrt57pdpub}, abstract = {Ageing trend in populations is correlated with increased prevalence of acquired cognitive impairments such as dementia. Although there is no cure for dementia, a timely diagnosis helps in obtaining necessary support and appropriate medication. With this in mind, researchers are working urgently to develop effective technological tools that can help doctors undertake early identification of cognitive disorder. In this paper, we introduce an automatic dementia screening system for ageing Deaf signers of British Sign Language (BSL), using Convolutional Neural Networks (CNN), by analysing the sign space envelope and facial expression of BSL signers using normal 2D videos from BSL corpus. Our approach firstly establishes an accurate real-time hand trajectory tracking model together with a real-time landmark facial motion analysis model to identify differences in sign space envelope and facial movement as the keys to identifying language changes associated with dementia. Based on the differences in patterns obtained from facial and trajectory motion data, CNN models (ResNet50/VGG16) are fine-tuned using Keras deep learning models to incrementally identify and improve dementia recognition rates. We report the results for two methods using different modalities (sign trajectory and facial motion), together with the performance comparisons between different deep learning CNN models in ResNet50 and VGG16. The experiments show the effectiveness of our deep learning based approach in terms of sign space tracking, facial motion tracking and early stage dementia performance assessment tasks. The results are validated against cognitive assessment scores as of our ground truth data with a test set performance of 87.88{\%}. The proposed system has potential for economical, simple, flexible, and adaptable assessment of other acquired neurological impairments associated with motor changes, such as stroke and Parkinson's disease in both hearing and Deaf people.} } @inproceedings{miyazaki:20002:sign-lang:lrec, author = {Miyazaki, Taro and Morita, Yusuke and Sano, Masanori}, title = {Machine Translation from Spoken Language to Sign Language using Pre-trained Language Model as Encoder}, pages = {139--144}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20002.html}, doi = {10.63317/39wgg62q9krg}, abstract = {Sign language is the first language for those who were born deaf or lost their hearing in early childhood, so such individuals require services provided with sign language. To achieve flexible open-domain services with sign language, machine translations into sign language are needed. Machine translations generally require large-scale training corpora, but there are only small corpora for sign language. To overcome this data-shortage scenario, we developed a method that involves using a pre-trained language model of spoken language as the initial model of the encoder of the machine translation model. We evaluated our method by comparing it to baseline methods, including phrase-based machine translation, using only 130,000 phrase pairs of training data. Our method outperformed the baseline method, and we found that one of the reasons of translation error is from pointing, which is a special feature used in sign language. We also conducted trials to improve the translation quality for pointing. The results are somewhat disappointing, so we believe that there is still room for improving translation quality, especially for pointing.} } @inproceedings{mocialov:20003:sign-lang:lrec, author = {Mocialov, Boris and Turner, Graham and Hastie, Helen}, title = {Towards Large-Scale Data Mining for Data-Driven Analysis of Sign Languages}, pages = {145--150}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20003.html}, doi = {10.63317/54bx8v7bb76v}, abstract = {Access to sign language data is far from adequate. We show that it is possible to collect the data from social networking services such as TikTok, Instagram, and YouTube by applying data filtering to enforce quality standards and by discovering patterns in the filtered data, making it easier to analyse and model. Using our data collection pipeline, we collect and examine the interpretation of songs in both the American Sign Language (ASL) and the Brazilian Sign Language (Libras). We explore their differences and similarities by looking at the co-dependence of the orientation and location phonological parameters.} } @inproceedings{moncrief:20018:sign-lang:lrec, author = {Moncrief, Robyn}, title = {Extending a Model for Animating Adverbs of Manner in {American} {Sign} {Language}}, pages = {151--156}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20018.html}, doi = {10.63317/3zzo3djnjkej}, abstract = {The goal of this work is to show that a model produced to characterize adverbs of manner can be applied to a variety of neutral animated signs to be used towards avatar sign language synthesis. This case study presents the extension of a new approach that was first presented at SLTAT 2019 in Hamburg for modeling language processes that manifest themselves as modifications to the manual channel. This work discusses additions to the model to be effective for one-handed and two-handed signs, repeating and non-repeating signs, and signs with contact.} } @inproceedings{muller:20025:sign-lang:lrec, author = {M{\"u}ller, Anke and Hanke, Thomas and Konrad, Reiner and Langer, Gabriele and W{\"a}hl, Sabrina}, title = {From Dictionary to Corpus and Back Again -- Linking Heterogeneous Language Resources for {DGS}}, pages = {157--164}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20025.html}, doi = {10.63317/4kr3gbtpykn9}, abstract = {The Public DGS Corpus is published in two different formats, that is subtitled videos for lay persons and lemmatized and annotated transcripts and videos for experts. In addition, a draft version with the first set of preliminary entries of the DGS dictionary (DW-DGS) to be completed in 2023 is now online. The Public DGS Corpus and the DW-DGS are conceived of as stand-alone products, but are nevertheless closely interconnected to offer additional and complementary informative functions. In this paper we focus on linking the published products in order to provide users access to corpus and corpus-based dictionary in various, interrelated ways. We discuss which links are thought to be useful and what challenges the linking of the products poses. In addition we address the inclusion of links to other, older lexical resources (LSP dictionaries).} } @inproceedings{mukushev:20036:sign-lang:lrec, author = {Mukushev, Medet and Imashev, Alfarabi and Kimmelman, Vadim and Sandygulova, Anara}, title = {Automatic Classification of Handshapes in {Russian} {Sign} {Language}}, pages = {165--170}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20036.html}, doi = {10.63317/4fzv7aim6uv3}, abstract = {Handshapes are one of the basic parameters of signs, and any phonological or phonetic analysis of a sign language must account for handshapes. Many sign languages have been carefully analysed by sign language linguists to create handshape inventories. This has theoretical implications, but also applied use, as it is important due to the need of generating corpora for sign languages that can be searched, filtered, sorted by different sign components (such as handshapes, orientation, location, movement, etc.). However, it is a very time-consuming process, thus only a handful of sign languages have such inventories. This work proposes a process of automatically generating such inventories for sign languages by applying automatic hand detection, cropping, and clustering techniques. We applied our proposed method to a commonly used resource: the Spreadthesign online dictionary (www.spreadthesign.com), in particular to Russian Sign Language (RSL). We then manually verified the data to be able to perform classification. Thus, the proposed pipeline can serve as an alternative approach to manual annotation, and can help linguists in answering numerous research questions in relation to handshape frequencies in sign languages.} } @inproceedings{nadal:20008:sign-lang:lrec, author = {Nadal, Camille and Collet, Christophe}, title = {Design and Evaluation for a Prototype of an Online Tool to Access Mathematics Notions in Sign Language}, pages = {171--176}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20008.html}, doi = {10.63317/534wbtkcoqpg}, abstract = {The Sign'Maths project aims at giving access to pedagogical resources in Sign Language (SL). It will provide Deaf students and teachers with mathematics vocabulary in SL, this in order to contribute to the standardisation of the vocabulary used at school. The work conducted led to Sign'Maths, an online interactive tool that gives Deaf students access to mathematics definitions in SL. A group of mathematics teachers for Deafs and teachers experts in SL collaborated to create signs to express mathematics concepts, and to produce videos of definitions, examples and illustrations for these concepts. In parallel, we are working on the conception and the design of Sign'Maths software and user interface. Our research work investigated ways to include SL in pedagogical resources in order to present information but also to navigate through the content. User tests revealed that users appreciate the use of SL in a pedagogical resource. However, they pointed out that SL content should be complemented with French to support bilingual education. Our final solution takes advantage of the complementarity of SL, French and visual content to provide an interface that will suit users no matter what their education background is. Future work will investigate a tool for text and signs' search within Sign'Maths.} } @inproceedings{oqvist:20014:sign-lang:lrec, author = {{\"O}qvist, Zrajm and Riemer Kankkonen, Nikolaus and Mesch, Johanna}, title = {{STS-korpus}: A Sign Language Web Corpus Tool for Teaching and Public Use}, pages = {177--180}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20014.html}, doi = {10.63317/2rr58psftbxo}, abstract = {In this paper we describe STS-korpus, a web corpus tool for Swedish Sign Language (STS) which we have built during the past year, and which is now publicly available on the internet. STS-korpus uses the data of Swedish Sign Language Corpus (SSLC) and is primarily intended for teachers and students of sign language. As such it is created to be simple and user-friendly with no download or setup required. The user interface allows for searching -- with search results displayed as a simple concordance -- and viewing of videos with annotations. Each annotation also provides additional data and links to the corresponding entry in the online Swedish Sign Language Dictionary. We describe the corpus, its appearance and search syntax, as well as more advanced features like access control and dynamic content. Finally we say a word or two about the role we hope it will play in the classroom, and something about the development process and the software used. STS-korpus is available here: https://teckensprakskorpus.su.se} } @inproceedings{ozdemir:20005:sign-lang:lrec, author = {{\"O}zdemir, O{\u g}ulcan and K{\i}nd{\i}ro{\u g}lu, Ahmet Alp and Camg{\"o}z, Necati Cihan and Akarun, Lale}, title = {{BosphorusSign22k} Sign Language Recognition Dataset}, pages = {181--188}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20005.html}, doi = {10.63317/34i5aeztu5zn}, abstract = {Sign Language Recognition is a challenging research domain. It has recently seen several advancements with the increased availability of data. In this paper, we introduce the BosphorusSign22k, a publicly available large scale sign language dataset aimed at computer vision, video recognition and deep learning research communities. The primary objective of this dataset is to serve as a new benchmark in Turkish Sign Language Recognition for its vast lexicon, the high number of repetitions by native signers, high recording quality, and the unique syntactic properties of the signs it encompasses. We also provide state-of-the-art human pose estimates to encourage other tasks such as Sign Language Production. We survey other publicly available datasets and expand on how BosphorusSign22k can contribute to future research that is being made possible through the widespread availability of similar Sign Language resources. We have conducted extensive experiments and present baseline results to underpin future research on our dataset.} } @inproceedings{polat:20033:sign-lang:lrec, author = {Polat, Korhan and Sara{\c c}lar, Murat}, title = {Unsupervised Term Discovery for Continuous Sign Language}, pages = {189--196}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20033.html}, doi = {10.63317/25vd2bu88o4b}, abstract = {Most of the sign language recognition (SLR) systems rely on supervision for training and available annotated sign language resources are scarce due to the difficulties of manual labeling. Unsupervised discovery of lexical units would facilitate the annotation process and thus lead to better SLR systems. Inspired by the unsupervised spoken term discovery in speech processing field, we investigate whether a similar approach can be applied in sign language to discover repeating lexical units. We adapt an algorithm that is designed for spoken term discovery by using hand shape and pose features instead of speech features. The experiments are run on a large scale continuous sign corpus and the performance is evaluated using gloss level annotations. This work introduces a new task for sign language processing that has not been addressed before.} } @inproceedings{salonen:20004:sign-lang:lrec, author = {Salonen, Juhana and Kronqvist, Antti and Jantunen, Tommi}, title = {The Corpus of {Finnish} {Sign} {Language}}, pages = {197--202}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20004.html}, doi = {10.63317/3g9zmxomn7so}, abstract = {This paper presents the Corpus of Finnish Sign Language (Corpus FinSL), a structured and annotated collection of Finnish Sign Language (FinSL) videos published in May 2019 in FIN-CLARIN's Language Bank of Finland. The corpus is divided into two subcorpora, one of which comprises elicited narratives and the other conversations. All of the FinSL material has been annotated using ELAN and the lexical database Finnish Signbank. Basic annotation includes ID-glosses and translations into Finnish. The anonymized metadata of Corpus FinSL has been organized in accordance with the IMDI standard. Altogether, Corpus FinSL contains nearly 15 hours of video material from 21 FinSL users. Corpus FinSL has already been exploited in FinSL research and teaching, and it is predicted that in the future it will have a significant positive impact on these fields as well as on the status of the sign language community in Finland.} } @inproceedings{sevilla:20023:sign-lang:lrec, author = {Sevilla, Antonio F. G. and D{\'i}az Esteban, Alberto and Lahoz-Bengoechea, Jos{\'e} Mar{\'i}a}, title = {Tools for the use of {SignWriting} as a Language Resource}, pages = {203--208}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20023.html}, doi = {10.63317/4g9c2355h2bu}, abstract = {Representation of linguistic data is an issue of utmost importance when developing language resources, but the lack of a standard written form in sign languages presents a challenge. Different notation systems exist, but only SignWriting seems to have some use in the native signer community. It is, however, a difficult system to use computationally, not based on a linear sequence of characters. We present the project "VisSE", which aims to develop tools for the effective use of SignWriting in the computer. The first of these is an application which uses computer vision to interpret SignWriting, understanding the meaning of new or existing transcriptions, or even hand-written images. Two additional tools will be able to consume the result of this recognizer: first, a textual description of the features of the transcription will make it understandable for non-signers. Second, a three-dimensional avatar will be able to reproduce the configurations and movements contained within the transcription, making it understandable for signers even if not familiar with SignWriting. Additionally, the project will result in a corpus of annotated SignWriting data which will also be of use to the computational linguistics community.} } @inproceedings{skobov:20001:sign-lang:lrec, author = {Skobov, Victor and Lepage, Yves}, title = {{Video-to-HamNoSys} Automated Annotation System}, pages = {209--216}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20001.html}, doi = {10.63317/38okj9ehyfwh}, abstract = {The Hamburg Notation System (HamNoSys) was developed for movement annotation of any sign language (SL) and can be used to produce signing animations for a virtual avatar with the JASigning platform. This provides the potential to use HamNoSys, i.e., strings of characters, as a representation of an SL corpus instead of video material. Processing strings of characters instead of images can significantly contribute to sign language research. However, the complexity of HamNoSys makes it difficult to annotate without a lot of time and effort. Therefore annotation has to be automatized. This work proposes a conceptually new approach to this problem. It includes a new tree representation of the HamNoSys grammar that serves as a basis for the generation of grammatical training data and classification of complex movements using machine learning. Our automatic annotation system relies on HamNoSys grammar structure and can potentially be used on already existing SL corpora. It is retrainable for specific settings such as camera angles, speed, and gestures. Our approach is conceptually different from other SL recognition solutions and offers a developed methodology for future research.} } @inproceedings{tamer:20032:sign-lang:lrec, author = {Tamer, Nazif Can and Sara{\c c}lar, Murat}, title = {Cross-Lingual Keyword Search for Sign Language}, pages = {217--223}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20032.html}, doi = {10.63317/4mwxcbiwhy7n}, abstract = {Sign language research most often relies on exhaustively annotated and segmented data, which is scarce even for the most studied sign languages. However, parallel corpora consisting of sign language interpreting are rarely explored. By utilizing such data for the task of keyword search, this work aims to enable information retrieval from sign language with the queries from the translated written language. With the written language translations as labels, we train a weakly supervised keyword search model for sign language and further improve the retrieval performance with two context modeling strategies. In our experiments, we compare the gloss retrieval and cross language retrieval performance on RWTH-PHOENIX-Weather 2014T dataset.} } @inproceedings{trevino:20038:sign-lang:lrec, author = {Trevi{\~n}o, Rafael O. and Hochgesang, Julie A. and Shaw, Emily P. and Willow, Nic}, title = {One Side of the Coin: Development of an {ASL-English} Parallel Corpus by Leveraging {SRT} Files}, pages = {224--230}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20038.html}, doi = {10.63317/29er8w7km4yi}, abstract = {We report on a method used to develop a sizable parallel corpus of English and American Sign Language (ASL). The effort is part of the Gallaudet University Documentation of ASL (GUDA) project, which is currently coordinated by an interdisciplinary team from the Department of Linguistics and the Department of Interpretation and Translation at Gallaudet University. Creation of the parallel corpus makes use of the available SRT (SubRip Subtitle) files of ASL videos that have been interpreted into or from English, or captioned into English. The corpus allows for one-way searches based on the English translation or interpretation, which is useful for translators, interpreters, and those conducting comparative analyses. We conclude with a discussion of important considerations for this method of constructing a parallel corpus, as well as next steps that will help to refine the development and utility of this type of corpus.} } @proceedings{lrec:sign-lang:18, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, title = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, url = {https://www.sign-lang.uni-hamburg.de/lrec2018/LREC2018_W1_SIGN-LANG_PROCEEDINGS.pdf} } @inproceedings{alkhazraji:18013:sign-lang:lrec, author = {Al-khazraji, Sedeeq and Kafle, Sushant and Huenerfauth, Matt}, title = {Modeling and Predicting the Location of Pauses for the Generation of Animations of {American} {Sign} {Language}}, pages = {1--6}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18013.html}, abstract = {Adding American Sign Language (ASL) animation to websites can improve information access for people who are deaf with low levels of English literacy. Given a script representing the sequence of ASL signs, we must generate an animation, but a challenge is selecting accurate speed and timing for the resulting animation. In this work, we analyzed motion-capture data recorded from human ASL signers to model the realistic timing of ASL movements, with a focus on where to insert prosodic breaks (pauses), based on the sentence syntax and other features. Our methodology includes extracting data from a pre-existing ASL corpus at our lab, selecting suitable features, and building machine learning models to predict where to insert pauses. We evaluated our model using cross-validation and compared various subsets of features. Our model had 80{\%} accuracy at predicting pause locations, out-performing a baseline model on this task.} } @inproceedings{bono:18027:sign-lang:lrec, author = {Bono, Mayumi and Sakaida, Rui and Makino, Ryosaku and Okada, Tomohiro and Kikuchi, Kouhei and Cibulka, Mio and Willoughby, Louisa and Iwasaki, Shimako and Fukushima, Satoshi}, title = {Tactile {Japanese} {Sign} {Language} and Finger {Braille}: An Example of Data Collection for Minority Languages in {Japan}}, pages = {7--14}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18027.html}, abstract = {We recorded data on deafblind people in Japan. In this filming project, we found that Japanese deafblind people use different communication methods, tactile Japanese sign language and finger braille, depending on their hearing ability and eyesight. Tactile sign language is normally used by those who were born deaf or lost their hearing at an early age and then lost their sight after acquiring a sign language. These people are known as deaf-based deafblind (D-deafblind). Finger braille is popular in Japan, but largely unknown elsewhere. It is normally used by those who were born blind or lost their sight at an early age and subsequently lost their hearing after learning how to produce speech using their throat and mouth. These people are known as blind-based deafblind (B-deafblind hereafter). This paper introduces our filming project; the ways of data collection, translation and annotation. In addition, we show our preliminary observations using our data sets to clarify the important fact that we should collect their interactions at this moment. The data show how their interactions have already become established and sophisticated in their communities. We discuss how our filming project will contribute to the deafblind community in Japan.} } @inproceedings{brock:18012:sign-lang:lrec, author = {Brock, Heike and Rengot, Juliette and Nakadai, Kazuhiro}, title = {Augmenting Sparse Corpora for Enhanced Sign Language Recognition and Generation}, pages = {15--22}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18012.html}, abstract = {The collection of signed utterances for recognition and generation of Sign Language (SL) is a costly and labor-intensive task. As a result, SL corpora are usually considerably smaller than their spoken language or image data counterparts. This is problematic, since the accuracy and applicability of a neural network depends largely on the quality and amount of its underlying training data. Common data augmentation strategies to increase the number of available training data are usually not applicable to the spatially and temporally constrained motion sequences of a SL corpus. In this paper, we therefore discuss possible data manipulation methods on the base of a collection of motion-captured SL sentence expressions. Evaluation of differently trained network architectures shows a significant reduction of overfitting by inclusion of the augmented data. Simultaneously, the accuracy of both sign recognition and generation was improved, indicating that the proposed data augmentation methods are beneficial for constrained and sparse data sets.} } @inproceedings{cibulka:18032:sign-lang:lrec, author = {Cibulka, Mio}, title = {Communication Across Sensorial Divides -- A Proposed Community Sourced Corpus of Everyday Interaction between Deaf Signers and Hearing Nonsigners}, pages = {23--28}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18032.html}, abstract = {While research on conversation in signed and spoken languages has been flourishing, research on their intersection is scarce. This paper presents an ongoing project that gathers and analyses video data from deaf people's everyday interaction with hearing nonsigners and considers possibilities of involving the communication community that is at its centre and participant empowerment. The scope is to investigate the organisation and structure of communication in which linguistic resources are less accessible and in which social meaning tends to emerge from the interactants' online analysis of the local context (e.g., spatial environment, bodily configurations and movement of the interactants).} } @inproceedings{clark:18035:sign-lang:lrec, author = {Clark, Brenda and Clark, Greg}, title = {{SiLOrB} and {Signotate}: A Proposal for Lexicography and Corpus-building via the Transcription, Annotation, and Writing of Signs}, pages = {29--32}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18035.html}, abstract = {This paper proposes a system of standardized transcription and orthographic representation for sign languages (Sign Language Orthography Builder) with a corresponding text-based corpus-building and annotation tool (Signotate). The transcription system aims to be analogous to IPA in using ASCII characters as a standardized way to represent the phonetic aspects of any sign, and the writing system aims to be transparent and easily readable, using pictographic symbols which combine to create a 'signer' in front of the reader. The proposed software can be used to convert transcriptions to written signs, and to create annotated corpora or lexicons. Its text-based human- and machine-readable format gives a user the ability to search large quantities of data for a variety of features and contributes to sources, such as dictionaries and transcription corpora.} } @inproceedings{efthimiou:18046:sign-lang:lrec, author = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Kakoulidis, Panos and Goulas, Theodoros}, title = {Terminology Enrichment through Crowd Sourcing at {PYLES} Platform}, pages = {33--38}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18046.html}, abstract = {The Information System PYLES is a management system for on-line lessons, designed to support accesible asynchronous e-learning, addressing learning needs of students with various communication capabilities and needs at the Technological Educational Institute of Athens (TEI-A). It, thus, exploits both uptodate assistive technology software and content in various forms. This platform has been used as the basis for the development of an active repository of multimodal educational resources, also incorporating a terminology lexicon for the Greek Sign Language (GSL) and a general purpose dictionary of GSL. The platform provides advanced customization options according to user needs but also a collaborative environment for the support of teaching and learning processes. The information system (http://eclassamea.teiath.gr/ ) is built on the open code platform `Open eClass' (http://www.openeclass.org/), a free e-learning platform that it actually enriches with tools and functionalities which allow extended accessibility regarding both the environment and the educational content. Regarding customization to serve GSL signers' needs, the platform incorporates: - Selected lesson presentations in GSL on the basis of deaf students' preferences regarding the curriculum offers - An on line dictionary of general purpose lemma list - An on line terminology glossary - Administrative form related information in GSL Following the Open eClass patern, three basic user roles are supported: (i) student, (ii) instructor, and (iii) administrator. However, the platform also supports special intermediary roles such as ``administrator assistant'', ``user administrator'', ``group leader'' and ``visitor''. These roles serve among other functionalities, the options available for lexical material enrichment through crowd sourcing. The GSL terminology environment allows for the creation of different glossaries directly by their users, where GSL signers are invited to upload their suggestions for various terms under specific quality control conditions. Authorized users may enter new terminology items including the term definition and various supporting multimedia material (icons, video, text etc), while they can modify or completely delete entries. Furthermore, they can validate terms suggested by non authorized users to make them visible to the whole user community. Terminology enrichment actions incorporate: 1. New lemma or new sense entry 2. Modification of a lemma or a sense3. Validation of a proposed lemma sense 4. Communication or hiding of a lemma sense or a lemma description 5. Linking of a lemma with a lemma in a different language (Greek and/or English)} } @inproceedings{efthimiou:18043:sign-lang:lrec, author = {Efthimiou, Eleni and Vasilaki, Kyriaki and Fotinea, Stavroula-Evita and Vacalopoulou, Anna and Goulas, Theodoros and Dimou, Athanasia-Lida}, title = {The {POLYTROPON} Parallel Corpus}, pages = {39--44}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18043.html}, abstract = {Here we present the POLYTROPON parallel corpus for the language pair Greek Sign Language (GSL) -- Greek, which is created and annotated aiming to serve as a golden corpus available to the community of SL technologies for experimentation with various approaches to SL processing, focusing on machine learning for SL recognition, machine translation (MT) and information retrieval. The corpus volume incorporates 3653 clauses in three repetitions each, captured in front view by means of one HD and one kinect camera. Corpus annotation has allowed to extract initial features sets with the aim to reach a GSL level of abstraction close to the one currently available for Greek language representations, exploiting the inherent characteristics of the language in view of applying initial deep learning experiments on GSL data, where both words and signs may be represented as vectors of characteristics which allow dependency tree structure representations of input text and signed clauses as those created by the use of Tree Editor TrEd 2.0.} } @inproceedings{filhol:18024:sign-lang:lrec, author = {Filhol, Michael and McDonald, John C.}, title = {Extending the {AZee-Paula} Shortcuts to Enable Natural Proform Synthesis}, pages = {45--52}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18024.html}, abstract = {Proform structures such as classifier predicates have traditionally challenged Sign Language (SL) synthesis systems, particularly in respect to the production of smooth natural motion. To address this issue a synthesizer must necessarily leverage a structured linguistic model for such constructs to specify the linguistic constraints, and also an animation system that is able to provide natural avatar motion within the confines of those constraints. The proposed system bridges two existing technologies, taking advantage of the ability of AZee to encode both the form and functional linguistic aspects of the proform movements and on the Paula avatar system to provide convincing human motion. The system extends a previous principle that more natural motion arises from leveraging knowledge of larger structures in the linguistic description.} } @inproceedings{gibet:18020:sign-lang:lrec, author = {Gibet, Sylvie}, title = {Building {French} {Sign} {Language} Motion Capture Corpora for Signing Avatars}, pages = {53--58}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18020.html}, abstract = {The design of traditional corpora for linguistic analysis aims to provide living representations of sign languages across deaf communities and linguistic researchers. Most of the time, the sign language data is video-recorded and then encoded in a standardized and homogenous structure for open-ended analysis (statistical or phonological studies). With such structures, sign language corpora are described and annotated into linguistic components, including phonology, morphology, and syntactic components. Conversely, motion capture (MoCap) corpora provide researchers the data necessary to carry on finer-grained studies on movement, thus allowing precise, and quantitative analysis of sign language gestures as well as sign language (SL) generation. One the one hand, motion data serves to validate and enforce existing theories on the phonologies of sign languages. By aligning temporally motion trajectories and labelled linguistic information, it thus becomes possible to study the influence of the movement articulation on the linguistic aspects of the SL, including hand configuration, hand movement, co-articulation or synchronization within intra and inter phonological channels. On the other hand, generation pertains to sign production using animated virtual characters, usually called signing avatars. Although MoCap technology presents exciting future directions for sign language studies, tightly interlinking language components and signals, it still requires high technical skills for recording, post-processing data, and there are many unresolved challenges, with the need to simultaneously record body, hand motion, facial expressions, and gaze direction. Therefore, there are still few MoCap corpora that have been developed in the field of sign language studies. Some of them are dedicated to the analysis of articulation and prosody aspects of sign languages, whereas recent interest in avatar technology has led to develop corpora associated to data-driven synthesis. This paper describes four corpora that have been designed and built in our research team. These corpora have been recorded using MoCap and video equipment, and annotated according to multi-tiers linguistic templates. Each corpus has been designed for a specific linguistic purpose and is dedicated to data-driven synthesis, by replacing signs or groups of signs, by composing phonetic or phonological components, or by altering prosody in the produced sign language utterances.} } @inproceedings{hadjadj:18047:sign-lang:lrec, author = {Hadjadj, Mohamed Nassime}, title = {Modeling of Geographical Location in {French} {Sign} {Language} from a Semantically Compositional Grammar}, pages = {59--62}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18047.html}, abstract = {The use of the specificities related to the visuo-gesual modality of SL, such as the use of the signing space and the simultaneous articulation of multiple channels allows the signer to express structures in a more illustrative way. The description of this structure goes beyond the linear linguistic organization initially applied to describe spoken languages. In this paper, we are interested in modeling structures that rely on the signing space to designate the location of one object relative to another. We are particularly interested in the study of location of one place in relation to another one in French Sign Language (LSF). After a presentation of the corpus and the methodology followed to analyze it, we present the study carried out as well as the results obtained.} } @inproceedings{hochgesang:18049:sign-lang:lrec, author = {Hochgesang, Julie A.}, title = {{SLAAASh} and the {ASL} Deaf Communities (or ``so many gifs!'')}, pages = {63--68}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18049.html}, abstract = {The project Sign Language Acquisition, Annotation, Archiving and Sharing (SLAAASh) is a model for working with diverse ASL Deaf communities in all stages of the project. In this presentation, I highlight key steps in achieving this level of collaboration. First, I discuss the importance of sharing work with the community---a key form of reciprocity recognized by Deaf community members. Second, I discuss the importance of reflecting diversity, e.g., ensuring that ASL Signbank actors vary in age, gender, ethnicity, body type, and language experience. Third, I discuss the importance of incorporating feedback from stakeholders and show how the ASL Signbank actors have expressed different views that have impacted our development of the Signbank. Finally, I discuss the crucial component of building substantive community connections and maintaining them long-term. I end by discussing our own efforts to build community connections to date as well as planned future ones.} } @inproceedings{hochgesang:18048:sign-lang:lrec, author = {Hochgesang, Julie A. and Crasborn, Onno and Lillo-Martin, Diane}, title = {Building the {ASL} {Signbank}: Lemmatization Principles for {ASL}}, pages = {69--74}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18048.html}, abstract = {Following the example of other sign language researchers, we are creating a Signbank, a usage-based lexical database, to maintain consistent and systematic annotation information for American Sign Language (ASL). This tool, which will be available to the public, is currently being used in conjunction with an on-going effort to prepare corpora of sign language acquisition to share with the research community. This paper will briefly report on the development of the ASL Signbank, focusing on the adopted lemmatization principles. Lemmatization of ASL signs has never been done on a scale like this before - one that has been continually refreshed by actual usage data.} } @inproceedings{hong:18031:sign-lang:lrec, author = {Hong, Sung-Eun and Won, Seongok and Heo, Il and Lee, Hyunhwa}, title = {Development of an ``Integrative System for {Korean} {Sign} {Language} Resources''}, pages = {75--78}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18031.html}, abstract = {In 2015, the KSL Corpus Project started to create a linguistic corpus of the Korean Sign Language (KSL). The collected data contains about 90 hours of sign language videos. Almost 17 hours of this sign language data has been annotated in ELAN, a professional annotation tool developed by the Max-Planck-Institute of Psycholinguistics in the Netherlands. In the first phase of annotation the research project faced three major difficulties. First there was no lexicon or lexical database available that means the annotators had to list the used sign types and link them with video clips showing the sign type. Second, having numerous annotators it was a challenge to manage and distribute the hundreds of movies and ELAN files. Third it was very difficult to control the quality of the annotation. In order to solve these problems the ``Integrative System for Korean Sign Language Resources'' was developed. This system administrates the signed movies and annotations files and also keeps track of the lexical database. Since all annotation files are uploaded into the system, the system is also able to manipulate the ELAN files. For example, tags are overwritten in the annotation when the name of the type has changed.} } @inproceedings{hong:18008:sign-lang:lrec, author = {Hong, Sung-Eun and Won, Seongok and Heo, Il and Lee, Hyunhwa}, title = {Raising Awareness for a {Korean} {Sign} {Language} Corpus among the Deaf Community}, pages = {79--82}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18008.html}, abstract = {This paper contains strategies that need to be implemented before the sign language community can be involved in corpus work to raise awareness for the need of corpus work. The Korean Sign Language (KSL) Corpus Project began in order to create a linguistic corpus with 60 deaf native and near-native signers form the area of Seoul. In the process of building the KSL Corpus by collecting sign language data and annotating it the project was faced with the challenge that the concept of corpus was completely new to the Korean Deaf community. The KSL Corpus Project developed three strategies in order to inform and explain what the KSL Corpus is about. First, the research project produced numerous KSL videos and posted them on social networking websites in a weekly rhythm. Second, the project organized a workshop, where only deaf people were invited to participate. Third, the KSL Corpus project selected prominent Deaf people who were schooled and provided with corpus materials in order to inform others about KSL Corpus by connecting to their friends and families. The experiences and outcomes of the above strategies are of special importance since the data collection of the KSL Corpus is still in process.} } @inproceedings{jahn:18018:sign-lang:lrec, author = {Jahn, Elena and Konrad, Reiner and Langer, Gabriele and Wagner, Sven and Hanke, Thomas}, title = {Publishing {DGS} {Corpus} Data: Different Formats for Different Needs}, pages = {83--90}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18018.html}, abstract = {In 2010-2012, the DGS-Korpus project collected a large corpus of German Sign Language (DGS). Now, a substantial subset of the data is published, namely the Public DGS Corpus. We describe the considerations and decisions taken regarding what part of the data is to be made public, the necessary quality assurance measures to the data preparation as well as the formats of the published data. The corpus is published in three different ways in order to fulfil the needs of a variety of different users. First of all, the data is made available to the language community whose members allowed us to share their recorded language. In addition, we hope that a large number of non-scientific users with various backgrounds will find the data useful. Last but not least, we aim to make the data attractive for users with a scientific background and provide the possibility to conduct studies based on it, irrespective of whether they are familiar with DGS or not.} } @inproceedings{kimmelman:18010:sign-lang:lrec, author = {Kimmelman, Vadim and Khristoforova, Evegniia}, title = {Quotation in {Russian} {Sign} {Language}: A Corpus Study}, pages = {91--94}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18010.html}, abstract = {We studied how quotation is expressed in naturalistic discourse in Russian Sign Language (RSL). We studied a sub-corpus of the online corpus of RSL containing narratives by eleven signers from Moscow. We identified 341 instances of quotation, including reported speech and reported thoughts. We annotated syntactic, semantic, and prosodic properties of the found instances of quotation. We found out that quotative constructions in RSL have the same basic structure as similar constructions in other spoken and signed languages. Furthermore, similarly to quotation in other sign languages, quotation in RSL can be marked by head and/or body movement and change in eye gaze direction. However, all of these markers are clearly optional, and a considerable number of examples do not include any of these markers. Furthermore, we found that, judging by the behavior of indexicals, RSL narratives in our dataset have a very strong preference for using direct speech. We discuss theoretical implications of the RSL data to the theory of quotation in sign languages.} } @inproceedings{kimmelman:18011:sign-lang:lrec, author = {Kimmelman, Vadim and Klomp, Ulrika and Oomen, Marloes}, title = {Where Methods Meet: Combining Corpus Data and Elicitation in Sign Language Research}, pages = {95--100}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18011.html}, abstract = {We discuss three case studies on various grammatical phenomena in Russian Sign Language (RSL) and Sign Language of the Netherlands (NGT) in order to compare corpus-based and elicitation-based approaches to sign linguistics. Firstly, we investigate impersonal reference in RSL using corpus search, informal elicitation, and an acceptability judgment task. Secondly, we examine argument structure and pro-drop licensing in NGT psych verb constructions using corpus search and a supplementary acceptability judgment task. Thirdly, we investigate conditional clauses in NGT based on corpus search, and contrast the findings with those from elicitation-based studies of conditional clauses in other sign languages. The three case studies highlight both the merits and limitations of combining different research methods as well as illustrate some of the issues that arise from doing so -- and how they may be navigated. We conclude that corpus-based research serves to identify the boundaries of observed variation and describe both expected and unexpected patterns, while the underlying factors for these patterns can be investigated by eliciting data in more controlled contexts. Finally, we demonstrate that the differences in the results obtained via various research methods have important practical implications, in particular for sign language education.} } @inproceedings{kuder:18033:sign-lang:lrec, author = {Kuder, Anna and Filipczak, Joanna and Mostowski, Piotr and Rutkowski, Pawe{\l} and Johnston, Trevor}, title = {What Corpus-based Research on Negation in {Auslan} and {PJM} Tells Us about Building and Using Sign Language Corpora}, pages = {101--106}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18033.html}, abstract = {In this paper, we would like to discuss our current work on negation in Auslan (Australian Sign Language) and PJM (Polish Sign Language, polski j{\k e}zyk migowy) as an example of experience in using sign language corpus data for research purposes. We describe how we prepared the data for two detailed empirical studies, given similarities and differences between the Australian and Polish corpus projects. We present our findings on negation in both languages, which turn out to be surprisingly similar. At the same time, what the two corpus studies show seems to be quite different from many previous descriptions of sign language negation found in the literature. Some remarks on how to effectively plan and carry out the annotation process of sign language texts are outlined at the end of the present paper, as they might be helpful to other researchers working on designing a corpus. Our work leads to two main conclusions: (1) in many cases, usage data may not be easily reconciled with intuitions and assumptions about how sign languages function and what their grammatical characteristics are like, (2) in order to obtain representative and reliable data from large-scale corpora one needs to plan and carry out the annotation process very thoroughly.} } @inproceedings{langer:18026:sign-lang:lrec, author = {Langer, Gabriele and M{\"u}ller, Anke and W{\"a}hl, Sabrina}, title = {Queries and Views in {iLex} to Support Corpus-based Lexicographic Work on {German} {Sign} {Language} ({DGS})}, pages = {107--114}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18026.html}, abstract = {In the DGS-Korpus project the corpus is being used as the basis for lexicographic descriptions of signs in dictionary entries. In this process the lexicographers start from the data and type entry structures as found in the annotation database. While preparing a dictionary entry much of the work consists of manually going through a number of single tokens viewing the original data and available annotations. Findings are then categorised and summarised. However, a number of decisions and descriptions are also supported by pre-defined searches and views on the data. Supported areas include lexicographic lemmatisation (lemma sign establishment), selection of citation forms and variants, grammatical behaviour of signs, collocational patterns of use, regional distribution patterns and distribution of lexical or formational variants over different age groups. While we are still in the process of exploring the possibilities of a sign language corpus for lexicography, searches and views that have proven useful for our work are exemplified in this paper with regard to dictionary entries.} } @inproceedings{malala:18028:sign-lang:lrec, author = {Malala, Vonjiniaina Domohina and Prigent, Elise and Braffort, Annelies and Berret, Bastien}, title = {Which Picture? A Methodology for the Evaluation of Sign Language Animation Understandability}, pages = {115--120}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18028.html}, abstract = {The goal of our study is to explore which information is essential to understand virtual signing. To that aim, we developed an online test to assess the comprehensibility of four different versions of signers: a baseline version with a real human signer, a most complete version of a virtual signer, and two degraded versions of a virtual signer (one with non-visible hands and one without movements of head/trunk). Each video showed the description of a picture in French Sign Language (LSF). After having seen the video, participants had to find which picture had been described among 9 pictures displayed. The originality of our approach was to include two types of confusable pictures on the response board. One was supposed to induce errors by confounding the lexical signs and the other by confounding the spatial structure of the picture. In this way, we explored the effect of hiding hands and blocking trunk/head on the comprehension of lexicon and spatial structure.} } @inproceedings{mesch:18019:sign-lang:lrec, author = {Mesch, Johanna and Sch{\"o}nstr{\"o}m, Krister}, title = {From Design and Collection to Annotation of a Learner Corpus of Sign Language}, pages = {121--126}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18019.html}, abstract = {This paper aims to present part of the project ``From Speech to Sign -- learning Swedish Sign Language as a second language'' which include a learner corpus that is based on data produced by hearing adult L2 signers. The paper describes the design of corpus building and the collection of data for the Corpus in Swedish Sign Language as a Second Language (SSLC-L2). Another component of ongoing work is the creation of a specialized annotation scheme for SSLC-L2, one that differs somewhat from the annotation work in Swedish Sign Language Corpus (SSLC), where the data is based on performance by L1 signers. Also, we will account for and discuss the methodology used to annotate L2 structures.} } @inproceedings{metaxas:18005:sign-lang:lrec, author = {Metaxas, Dimitris and Dilsizian, Mark and Neidle, Carol}, title = {Scalable {ASL} Sign Recognition using Model-based Machine Learning and Linguistically Annotated Corpora}, pages = {127--132}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18005.html}, abstract = {We report on the high success rates of our new, scalable, signer-independent, computational approach for sign recognition from monocular video, exploiting linguistically annotated ASL data sets. We recognize signs using a hybrid framework that combines state-of-the-art learning methods with features based on what is known about the linguistic composition of lexical signs. We model and recognize the sub-components of sign production, with attention to hand shape, orientation, location, motion trajectories, as well as facial features, and we combine these within a CRF framework. The effect is to make the sign recognition problem robust, scalable, and feasible with relatively smaller datasets than are required for purely data-driven methods. From a 350-sign vocabulary of isolated, citation-form lexical signs from the American Sign Language Lexicon Video Dataset (ASLLVD), including both 1- and 2-handed signs, we achieve a top-1 accuracy of 93.6{\%} and a top-5 accuracy of 97.9{\%}. The high probability with which we can produce 5 sign candidates that contain the correct result opens the door to potential applications, as it is reasonable to provide a sign lookup functionality that offers the user 5 possible signs, in decreasing order of likelihood, with the user then asked to select the desired sign.} } @inproceedings{mostowski:18045:sign-lang:lrec, author = {Mostowski, Piotr and Kuder, Anna and Filipczak, Joanna and Rutkowski, Pawe{\l}}, title = {Workflow Management and Quality Control in the Development of the {PJM} Corpus: The Use of an Issue-Tracking System}, pages = {133--138}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18045.html}, abstract = {The main goal of the present paper is to describe a workflow management and quality assurance system used in the project of developing the Polish Sign Language (polski j{\k e}zyk migowy, PJM) Corpus currently underway at the University of Warsaw, Poland. To ensure a satisfactory level of annotation quality, we implemented an external issue tracking system as a basic tool to manage all stages of the annotation process: segmenting the video recording into individual signs, adding glosses to the delineated signs, segmenting text into clauses, translating text into written Polish and adding grammar tags marking different language phenomena. This paper offers a detailed overview of the procedures that we employ, illustrating the most important advantages and disadvantages of our approach and the choices we have made.} } @inproceedings{naert:18014:sign-lang:lrec, author = {Naert, Lucie and Reverdy, Cl{\'e}ment and Larboulette, Caroline and Gibet, Sylvie}, title = {Per Channel Automatic Annotation of Sign Language Motion Capture Data}, pages = {139--146}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18014.html}, abstract = {Manual annotation is an expensive and time consuming task partly due to the high number of linguistic channels that usually compose sign language data. In this paper, we propose to automatize the annotation of sign language motion capture data by processing each channel separately. Motion features (such as distances between joints or facial descriptors) that take advantage of the 3D nature of motion capture data and the specificity of the channel are computed in order to (i) segment and (ii) label the sign language data. Two methods of automatic annotation of French Sign Language utterances using similar processes are developed. The first one describes the automatic annotation of thirty-two hand configurations while the second method describes the annotation of facial expressions using a closed vocabulary of seven expressions. Results for the two methods are then presented and discussed.} } @inproceedings{neidle:18001:sign-lang:lrec, author = {Neidle, Carol and Opoku, Augustine and Dimitriadis, Gregory and Metaxas, Dimitris}, title = {New shared {\&} interconnected {ASL} resources: {SignStream{\textregistered}} 3 software; {DAI} 2 for web access to linguistically annotated video corpora; and a sign bank}, pages = {147--154}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18001.html}, abstract = {2017 marked the release of a new version of SignStream{\textregistered} software, designed to facilitate linguistic analysis of ASL video. SignStream{\textregistered} provides an intuitive interface for labeling and time-aligning manual and non-manual components of the signing. Version 3 has many new features. For example, it enables representation of morpho-phonological information, including display of handshapes. An expanding ASL video corpus, annotated through use of SignStream{\textregistered}, is shared publicly on the Web. This corpus (video plus annotations) is Web-accessible---browsable, searchable, and downloadable---thanks to a new, improved version of our Data Access Interface: DAI 2. DAI 2 also offers Web access to a brand new Sign Bank, containing about 10,000 examples of about 3,000 distinct signs, as produced by up to 9 different ASL signers. This Sign Bank is also directly accessible from within SignStream{\textregistered}, thereby boosting the efficiency and consistency of annotation; new items can also be added to the Sign Bank. Soon to be integrated into SignStream{\textregistered} 3 and DAI 2 are visualizations of computer-generated analyses of the video: graphical display of eyebrow height, eye aperture, and head position. These resources are publicly available, for linguistic and computational research and for those who use or study ASL.} } @inproceedings{nunnari:18044:sign-lang:lrec, author = {Nunnari, Fabrizio and Filhol, Michael and Heloir, Alexis}, title = {Animating {AZee} Descriptions Using Off-the-Shelf {IK} Solvers}, pages = {155--162}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18044.html}, abstract = {We propose to implement a bottom-up animation solution for the AZee system. No low-level AZee animation system exists yet, which hinders its effective implementation as Sign Language avatar input. This bottom-up approach delivers procedurally computed animations and, because of its procedural nature, it is capable of generating the whole possible range of gestures covered by AZee's symbolic description. The goal is not to compete on the ground of naturalness since movements are bound to look robotic like all bottom-up systems, but its purpose could be to be used as the missing low-level fallback for an existing top-down system. The proposed animation system is built on the top of a freely available 3D authoring tool and takes advantage of the tool's default IK solving routines.} } @inproceedings{oviedo:18021:sign-lang:lrec, author = {Oviedo, Alejandro and Kaul, Thomas and Klinner, Leonid and Griebel, Reiner}, title = {The {Cologne} {Corpus} of {German} {Sign} {Language} as {L2} ({C/CSL2}): Current Development Stand}, pages = {163--166}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18021.html}, abstract = {Since 2016 (Kaul et al., 2016) a German Sign Language (DGS) learner corpus (Granger et al., 2015) it has been building up at the University of Cologne. Primary data consist of around 60 hours of signed discourse in more than 1,250 individual files produced by 350 DGS hearing learners (312 female / 38 male) whose mother tongue is German. Data has been collected from A1 to C1 CEFR (Council of Europe, 2001) proficiency levels. A similar number of monologues and dialogues is included. Monologues (average duration 2.5 minutes) are mostly induced by an illustration or a video. Dialogues have an average duration of 8 minutes. Dialogues corresponding to the levels A1 to B2 are performed between the informant and a Deaf teacher. At advanced level (C1) dialogues show an interaction between two students. Metadata related to the videos includes age and gender of the informants as well as the proficiency level and semester of data collection. A part of the data corresponds to a longitudinal learner corpus (Granger et al., 2015). This is the case of a group of students who visited DGS-courses of different proficiency levels between mid-2015 and the end of 2017 and were filmed at different times along that period. The corpus is a work in progress. Our primary data are constantly being extended, since each semester new videos are added to the corpus (the tests presented by the students in the DGS courses as well as a number of videos produced and analyzed by the students in linguistics courses). Only around 6{\%} of the videos have received so far transcription: German glosses, translation into German and some linguistic tags have been included in ELAN (Crasborn {\&} Slotjes, 2008) files. Lemmatisation (Johnston, 2010) has been oriented using a lexical database of around 8,000 signs previously produced by our university to serve as teaching material. Current transcriptions also include a series of annotation lines with controlled vocabulary for word-classes, disfluencies (Oviedo et al., in press) and deviations from the DGS standard at phonetic-phonological, morphological and syntactic levels. The biggest challenge faced so far in the development of our corpus is the reluctance of students to authorize the use of the corpus outside our research group. We are only authorized to transcribe the videos and use the transcriptions as a data source. However, a small group of students have up to now authorized us to show their videos and/or video-pictures to external audiences. One strategy that has proved to be useful in obtaining data that can be shared is that of linking students to the tasks of transcription and linguistic analysis. During the 2016/2017 winter semester we held a seminar with masters students to train them in the transcription of their own signed recordings. At the end of the course, the majority of the participants gave us permission to use their videos in public demonstrations. References Kaul, Th.; Oviedo, A.; Griebel, R.; Klinner, L.; Pr{\"u}fer, T. {\&} Krumpen, M. (2016). C/CSL2, The Cologne Corpus of Sign Language as a Second Language. Poster presented at TaLC 12, University of Giessen, held on 21th July 2016. Granger, S.; Guilquin, G. {\&} Meunier, F. (Eds.) (2015). The Cambridge Handbook of Learner Corpus Research. Cambridge: Cambridge University Press. Council of Europe. 2001. Common European framework of reference for languages: Learning, teaching, assessment. Cambridge: Press Syndicate of the University of Cambridge. Crasborn, O. {\&} Sloetjes, H.. 2008. Enhanced ELAN functionality for sign language corpora. In Onno Crasborn, Thomas Hanke, Eleni Efthimiou, Inge Zwitserlood {\&} Ernst Thoutenhoofd (Eds.). Proceedings of LREC 2008, Sixth International Conference on Language Resources and Evaluation. Paris: ELDA, pp. 39-43. Johnston, T. 2010. From archive to corpus: Transcription and annotation in the creation of signed language corpora. International Journal of Corpus Linguistics, 15(1), pp. 106-131. Oviedo, A.; Kaul, Th.; Urbann, K.; Griebel, R. {\&} Klinner, L. (in press): Eine Ann{\"a}herung zu den Pausen als Fl{\"u}ssigkeitsfaktoren in Deutscher Geb{\"a}rdensprache als L1. Das Zeichen 32(108). --to appear in March 2018.} } @inproceedings{oviedo:18004:sign-lang:lrec, author = {Oviedo, Alejandro and Ram{\'i}rez Valerio, Christian}, title = {The {LESCO} Corpus. Data for the Description of {Costa} {Rican} {Sign} {Language}}, pages = {167--170}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18004.html}, abstract = {LESCO is the most widely used sign language among Deaf people in Costa Rica (Woodward 1992). There are no precise figures available on the number of LESCO users, who live mostly in urban areas of the Central Valley of the country. Between 2010 and 2013 the Costa Rican government funded a project for a first linguistic description of LESCO, as a step towards recognition of the rights of Deaf people. The study of LESCO was based on the Corpus LESCO, a group of transcribed videos collected from Deaf signers from the main cities of the country along 2011. The project was carried on by a group consisted of five Deaf native LESCO-users and a hearing person with a good command of this sign language. A series of interviews were done over several months throughout the country allowing a pre-selection of 102 potential informants (all of them attesting a relative early LESCO acquisition, frequent use of LESCO, high degree of hearing-impairment, etc.). These people were video-recorded and so nearly 200 video-files (over 2000 minutes of footage) were obtained. Films included induced stories, life stories, free dialogues and interviews. For an initial description of the language, a selection of 44 files was transcribed on the basis of ELAN. Variants of each sign were identified and assigned to a particular lexeme. This process allowed the definition of more than 1,500 lemmas (Johnston 2010) from a total of around 14,000 lexical occurrences. The Corpus LESCO underpinned the construction of a basic dictionary (1,100 entries) and the drafting of a basic descriptive grammar of this sign language. Both dictionary and grammar are available online since the beginning of 2014 (www.cenarec-lesco.org). These works are the second corpus-based descriptions of a signed language in Spanish speaking Latin America. A previous experienced was carried of in Colombia between 2000 and 2005 (Oviedo 2001, CyC 2005). The initial project did not include the extension of the corpus. Both the Corpus LESCO and the rest of videos collected during the project are archived by the institution that administered the project in Costa Rica. The poster offers details about the process of building up the corpus and about its main characteristics. References CyC (Instituto Caro y Cuervo) (2005). Diccionario B{\'a}sico de la Lengua de Se{\~n}as Colombiana. Bogot{\'a}: INSOR-Instituto Caro y Cuervo. Johnston, T. (2010). From archive to corpus: Transcription and annotation in the creation of signed language corpora. International Journal of Corpus Linguistics, 15(1). pp. 106-131. Oviedo, A. (2001). Apuntes para una gram{\'a}tica de la Lengua de Se{\~n}as Colombiana. Cali: Universidad del Valle/INSOR. Woodward, J. (1991). Sign language varieties in Costa Rica. Sign Language Studies (20), pp. 329-334.} } @inproceedings{riemerkankkonen:18022:sign-lang:lrec, author = {Riemer Kankkonen, Nikolaus and Bj{\"o}rkstrand, Thomas and Mesch, Johanna and B{\"o}rstell, Carl}, title = {Crowdsourcing for the {Swedish} {Sign} {Language} Dictionary}, pages = {171--176}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18022.html}, abstract = {In this paper, we describe how we are actively using the Swedish Sign Language (SSL) community in collecting and documenting signs and lexical variation for our language resources, particularly the online Swedish Sign Language Dictionary (SSLD). Apart from using the SSL Corpus as a source of input for new signs and lexical variation in the SSLD, we also involve the community in two ways: first, we interact with SSL signers directly at various venues, collecting signs and judgments about signs; second, we discuss sign usage, lexical variation, and sign formation with SSL signers on social media, particularly through a Facebook group in which we both actively engage in and monitor discussions about SSL. Through these channels, we are able to get direct feedback on our language documentation work and improve on what has become the main lexicographic resource for SSL. We describe the process of simultaneously using corpus data, judgment and elicitation data, and crowdsourcing and discussion groups for enhancing the SSLD, and give examples of findings pertaining to lexical variation resulting from this work.} } @inproceedings{rivera:18040:sign-lang:lrec, author = {Rivera, Joanna Pauline and Ong, Clement}, title = {Recognizing Non-manual Signals in {Filipino} {Sign} {Language}}, pages = {177--184}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18040.html}, abstract = {Filipino Sign Language (FSL) is a multi-modal language that is composed of manual signlas and non-manual signals. Very minimal research is done regarding non-manual signals (Martinez and Cabalfin, 2008) despite the fact that non-manual signals play a significant role in conversations as it can be mixed freely with manual signals (Cabalfin et al., 2012). For other Sign Languages, there have been numerous researches regarding non-manual; however, most of these focused on the semantic and/or lexical functions only. Research on facial expressions in sign language that convey emotions or feelings and degrees of adjectives is very minimal. In this research, an analysis and recognition of non-manual signals in Filipino Sign Language are performed. The non-manual signals included are Types of Sentences (i.e. Statement, Question, Exclamation), Degrees of Adjectives (i.e. Absence, Presence, High Presence), and Emotions (i.e. Happy, Sad, Fast-approaching danger, stationary danger). The corpus was built with the help of the FSL Deaf Professors, and the 5 Deaf participants who signed 5 sentences for each of the types in front of Microsoft Kinect sensor. Genetic Algorithm is applied for the feature selection, while Artificial Neural Network and Support Vector Machine is applied for classification.} } @inproceedings{sze:18037:sign-lang:lrec, author = {Sze, Felix and Lau, Kloris and Yu, Kevin}, title = {The {Hong} {Kong} {Sign} {Language} Browser}, pages = {185--188}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18037.html}, abstract = {This paper describes the design of the Hong Kong Sign Language Browser which was established for providing accessible online resources on the lexical variations of HKSL in order to support the promotion of sign language and other sign-related services in the local community. With continuous funding support from the government since 2012, local Deaf organizations and Deaf signers of diverse backgrounds are invited to contribute their sign language knowledge in the data collection and evaluation process. Each year Deaf informants proficient in HKSL are invited to CSLDS to provide signing data to a pre-defined list of lexical targets. Their signing data are analyzed and variants are identified. These video data are then placed in an online platform for local Deaf organizations for rating and comments, and they can contribute data as well if there are additional variants not yet covered in the initial round of data collection. Once finalized, the lexical variants are placed in the Hong Kong Sign Language Browser for free public access. For each lexical target, each variant is indicated by a different color. Variants that are more commonly used and seen by Deaf organizations are listed first whereas the least common variants are listed last.} } @inproceedings{takkinen:18038:sign-lang:lrec, author = {Takkinen, Ritva and Ker{\"a}nen, Jarkko and Salonen, Juhana}, title = {Depicting Signs and Different Text Genres: Preliminary Observations in the Corpus of {Finnish} {Sign} {Language}}, pages = {189--194}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18038.html}, abstract = {In this article we first discuss the different kinds of signs occurring in sign languages and then concentrate on depicting signs, especially on their classification in Finnish Sign Language. Then we briefly describe the corpora of Finland's sign languages (CFINSL). The actual study concerns the occurrences of depicting signs in CFINSL in different text genres, introductions, narratives and free discussions. Depicting signs occurred most frequently in narratives, second most frequently in discussions and least frequently in introductions. The most frequent depicting signs in all genres were those that depicted the whole entity moving or being located. The second most frequent were those signs that expressed the handling of entities. The least frequent depicting signs were those with size- and shape-tracing handshapes. The proportion of depicting signs of all the signs in each genre was 17.9{\%} in the narratives, 2.9{\%} in the discussions and 2.2{\%} in the introductions. In order to deepen the analysis, depicting signs will have to be investigated from the perspective of movement types and the use of one or two hands.} } @inproceedings{troelsgard:18009:sign-lang:lrec, author = {Troelsg{\aa}rd, Thomas and Kristoffersen, Jette}, title = {Improving Lemmatisation Consistency without a Phonological Description. The {Danish} {Sign} {Language} Corpus and Dictionary Project.}, pages = {195--198}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18009.html}, abstract = {The Danish Sign Language Corpus and Dictionary project at Centre for Sign Language, UCC has a dual aim: to build of Danish Sign Language Corpus, and to use this corpus to expand and improve The Danish Sign Language Dictionary. Our goal is a one-to-one correspondence between sign lemmas in corpus and dictionary, but due to limited resources, we cannot include an accurate phonological description of each sign form. In order to secure a consistent lemmatisation in the corpus as well as across the two resources, we thus rely exclusively on sign videos and Danish equivalents. In this paper, we will describe how we use the lemmas of the Danish Sign Language Dictionary, and additional signs found in connection with the dictionary work, as the initial lexical database of the corpus tool. For new signs found in corpus, the actual corpus tokens will serve as preliminary video representations. To facilitate the sign search when lemmatising corpus tokens, we assign several Danish equivalents to each sign, including all equivalents in the dictionary data. Furthermore, we include synonyms found through linking these equivalents to the Danish wordnet (DanNet), although equivalents added in this way cannot be regarded as valid senses of the sign.} } @inproceedings{wahl:18025:sign-lang:lrec, author = {W{\"a}hl, Sabrina and Langer, Gabriele and M{\"u}ller, Anke}, title = {Hand in Hand - Using Data from an Online Survey System to Support Lexicographic Work}, pages = {199--206}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18025.html}, abstract = {In the DGS-Korpus project the lexicographic descriptions of signs are based on the available data of the DGS-Korpus, a reference corpus of German Sign Language (DGS). As this corpus is limited in size, number of informants recorded and topics included it is in some cases helpful to obtain additional information from the larger sign language community via an online voting system. This is done using the DGS-Feedback System, a tool especially designed for online surveys conducted using a sign language. With this tool further information on e.g. sign forms and meanings and their use and regional distribution has been elicited. Data from the DGS-Feedback is used in several ways during the lexicographic process of preparing dictionary entries to supplement data from the corpus. In the following the consideration of the data from the DGS-Feedback in relation to the corpus data in decision-making, analysis and lexicographic description is explained and discussed by way of examples.} } @inproceedings{wolfe:18023:sign-lang:lrec, author = {Wolfe, Rosalee and Hanke, Thomas and Langer, Gabriele and Jahn, Elena and Worseck, Satu and Bleicken, Julian and McDonald, John C. and Johnson, Sarah}, title = {Exploring Localization for Mouthings in Sign Language Avatars}, pages = {207--212}, editor = {Bono, Mayumi and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Osugi, Yutaka}, booktitle = {Proceedings of the {LREC2018} 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community}, maintitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {12}, month = may, year = {2018}, isbn = {979-10-95546-01-6}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/18023.html}, abstract = {According to the World Wide Web Consortium (W3C), localization is ``the adaptation of a product, application or document content to meet the language, cultural and other requirements of a specific target market''. One requirement necessary for localizing a sign language avatar is creating a capability to produce convincing mouthing. For purposes of this inquiry we make a distinction between mouthings and mouth gesture. The term `mouthings' refers to mouth movements derived from words of a spoken language whereas `mouth gesture' refers to mouth movements not derived from a spoken language. This effort focuses on the former. The prevalence of mouthings varies across different sign languages and individual signers. Although mouthings occur regularly in most sign languages, their significance and status have been a matter of sometimes heated discussions among sign linguists. However, no matter the theoretical viewpoint one takes on the issue of mouthing, one must acknowledge that for most if not all sign languages, mouthings do occur. If an avatar purports to fully and naturally express any sign language, it must have the capacity to express all aspects of the language, which likely will include mouthings. Although most avatar systems were created for hearing communities, several technologies have emerged to improve speech recognition for those who are hard-of-hearing or who find themselves in noisy environments. These were not satisfactory for Deaf communities as they did not portray sign language. Initial efforts to incorporate mouthing in sign language avatars utilized a mouth picture or viseme for each letter of the International Phonetic Alphabet (IPA), but were hampered by a reliance on blend shapes. Muscle-based avatars have the advantage of avoiding the limitations of blend shapes. This paper reports on a first step to identify the requirements for extending a muscle-based avatar to incorporate mouthings in multiple sign languages.} } @proceedings{lrec:sign-lang:16, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, title = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, url = {http://www.lrec-conf.org/proceedings/lrec2016/workshops/LREC2016Workshop-SignLanguage_Proceedings.pdf} } @inproceedings{bartha:16021:sign-lang:lrec, author = {Bartha, Csilla and Holecz, Margit and Varjasi, Szabolcs}, title = {The {SIGNificant} {Chance} Project and the Building of the First {Hungarian} {Sign} {Language} Corpus}, pages = {1--6}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16021.html}, abstract = {The Act CXXV of 2009 on Hungarian Sign Language and the Use of Hungarian Sign Language recognizes Hungarian Sign Language (HSL) as an independent natural language, moreover it provides the legal framework to introduce bilingual education (HSL-Hungarian) in 2017. In order to establish the linguistic background for bilingual education it was crucial to carry out linguistic research on HSL, which research should be sociolinguistically underpinned and should include corpus-based research. This research also aims to standardize HSL for educational purposes with the highest possible degree of community engagement. \par During the SIGNificant Chance project a sign language corpus (approximately 1750 hours) was created. A nation-wide fieldwork was conducted (five regions, nine venues). 147 sociolinguistic interviews and 27 grammatical tests (with 54 participants) were recorded in multiple-camera settings. There were also Hungarian competency tests and narrative interviews conducted with selected participants in order to make the complex description of their different linguistic practices in different discursive contexts possible. \par We are using ELAN and three different templates to analyze the collected data for different purposes (sociolinguistic-grammatical template, another for short term project purposes, and one for the dictionary). Some parts of the annotation work has been finished which contributed to the writing of the basic grammar of HSL and the creation of a small corpus-based dictionary of HSL.} } @inproceedings{benchiheub:16029:sign-lang:lrec, author = {Benchiheub, Mohamed-El-Fatah and Berret, Bastien and Braffort, Annelies}, title = {Collecting and Analysing a Motion-Capture Corpus of {French} {Sign} {Language}}, pages = {7--12}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16029.html}, abstract = {This paper presents a 3D corpus of motion capture data on French Sign Language (LSF), which is the first one available for the scientific community for pluridisciplinary studies. The paper also exhibits the usefulness of performing kinematic analysis on the corpus. The goal of the analysis is to acquire informative and quantitative knowledge for the purpose of better understanding and modelling LSF movements. Several LSF native signers are involved in the project. They were asked to describe 25 pictures in a spontaneous way while the 3D position of various body parts was recorded. Data processing includes identifying the markers, interpolating the information of missing frames, and importing the data to an annotation software to segment and classify the signs. Finally, we present the results of an analysis performed to characterize information-bearing parameters and use them in a data mining and modelling perspective.} } @inproceedings{borstell:16004:sign-lang:lrec, author = {B{\"o}rstell, Carl and {\"O}stling, Robert}, title = {Visualizing Lects in a Sign Language Corpus: Mining Lexical Variation Data in Lects of {Swedish} {Sign} {Language}}, pages = {13--18}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16004.html}, abstract = {In this paper, we discuss the possibilities for mining lexical variation data across (potential) lects in Swedish Sign Language (SSL). The data come from the SSL Corpus (SSLC), a continuously expanding corpus of SSL, its latest release containing 43307 annotated sign tokens, distributed over 42 signers and 75 time-aligned video and annotation files. After extracting the raw data from the SSLC annotation files, we created a database for investigating lexical distribution/variation across three possible lects, by merging the raw data with an external metadata file, containing information about the age, gender, and regional background of each of the 42 signers in the corpus. We go on to present a first version of an easy-to-use graphical user interface (GUI) that can be used as a tool for investigating lexical variation across different lects, and demonstrate a few interesting finds. This tool makes it easier for researchers and non-researchers alike to have the corpus frequencies for individual signs visualized in an instant, and the tool can easily be updated with future expansions of the SSLC.} } @inproceedings{borstell:16025:sign-lang:lrec, author = {B{\"o}rstell, Carl and Wiren, Mats and Mesch, Johanna and G{\"a}rdenfors, Moa}, title = {Towards an Annotation of Syntactic Structure in the {Swedish} {Sign} {Language} Corpus}, pages = {19--24}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16025.html}, abstract = {This paper describes on-going work on extending the annotation of the Swedish Sign Language Corpus (SSLC) with a level of syntactic structure. The basic annotation of SSLC in ELAN consists of six tiers: four for sign glosses (two tiers for each signer; one for each of a signer's hands), and two for written Swedish translations (one for each signer). In an additional step by {\"O}stling et al. (2015), all glosses of the corpus have been further annotated for parts of speech. Building on the previous steps, we are now developing annotation of clause structure for the corpus, based on meaning and form. We define a clause as a unit in which a predicate asserts something about one or more elements (the arguments). The predicate can be a (possibly serial) verbal or nominal. In addition to predicates and their arguments, criteria for delineating clauses include non-manual features such as body posture, head movement and eye gaze. The goal of this work is to arrive at two additional annotation tier types in the SSLC: one in which the sign language texts are segmented into clauses, and the other in which the individual signs are annotated for their argument types.} } @inproceedings{boyesbraem:16008:sign-lang:lrec, author = {Boyes Braem, Penny and Ebling, Sarah}, title = {Preventing Too Many Cooks from Spoiling the Broth: Some Questions and Suggestions for Collaboration between Projects in {iLex}}, pages = {25--28}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16008.html}, abstract = {Collaborative development of sign language resources is fortunately becoming increasingly common. In the spirit of collaboration, having one shared lexicon for sign language projects is a big advantage. However, this poses challenges to aspects pertaining to consistency of data, privacy of informants, and intellectual property. This contribution points out some problems that arise, especially if the common data comes from projects of different institutions. We describe what we have found to be a sustainable legal framework for our collaborative iLex corpus lexicon, giving an overview of the different kinds of partners involved in the creation and exploitation of a shared iLex corpus lexicon and providing our answers to the questions we faced along with an outlook for the future.} } @inproceedings{chenpichler:16028:sign-lang:lrec, author = {Chen Pichler, Deborah and Hochgesang, Julie A. and Simons, Doreen and Lillo-Martin, Diane}, title = {Community Input on Re-consenting for Data Sharing}, pages = {29--34}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16028.html}, abstract = {Development of large sign language corpora is on the rise, and online sharing of such corpora promises unprecedented access to high quality sign language data, with significant time-saving benefits for sign language acquisition research. Yet data sharing also brings complex logistical challenges for which few standardized practices exist, particularly with regard to the protection of participant rights. Although some ethical guidelines have been established for large-scale archiving of spoken or transcribed language data, not all of these are feasible for sign language video data, especially given the relatively small and historically vulnerable communities from which sign language data are typically collected. Our primary focus is the process of re-consenting participants whose original informed consent did not address the possibility of sharing their video data. We describe efforts to develop ethically sound, community-supported practices for data sharing and archiving, summarizing feedback collected from two focus groups including a cross-section of community stakeholders. Finally, we discuss general themes that emerged from the focus groups, placing them in the wider context of similar discussions previously published by other researchers grappling with these same issues, with the goal of contributing to best-practices guidelines for data archiving and sharing in the sign language research community.} } @inproceedings{cormier:16015:sign-lang:lrec, author = {Cormier, Kearsy and Crasborn, Onno and Bank, Richard}, title = {Digging into Signs: Emerging Annotation Standards for Sign Language Corpora}, pages = {35--40}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16015.html}, abstract = {This paper describes the creation of annotation standards for glossing sign language corpora as part of the Digging into Signs project (2014-2015). This project was based on the annotation of two major sign language corpora, the BSL Corpus (British Sign Language) and the Corpus NGT (Sign Language of the Netherlands). The focus of the gloss annotations in these data sets was in line with the starting point of most sign language corpora: to make general corpus annotation maximally useful regardless of the particular research focus. Therefore, the joint annotation guidelines that were the output of the project focus on basic annotation of hand activity, aiming to ensure that annotations can be made in a consistent way irrespective of the particular sign language. The annotation standard provides annotators with the means to create consistent annotations for various types of signs that in turn will facilitate cross-linguistic research. At the same time, the standard includes alternative strategies for some types of signs. In this paper we outline the key features of the joint annotation conventions arising from this project, describe the arguments around providing alternative strategies in a standard, as well as discuss reliability measures and improvement to annotation tools.} } @inproceedings{crasborn:16023:sign-lang:lrec, author = {Crasborn, Onno and Bank, Richard and Zwitserlood, Inge and van der Kooij, Els and Sch{\"u}ller, Anique and Ormel, Ellen and Nauta, Ellen Yassine and van Zuilen, Merel and van Winsum, Frouke and Ros, Johan}, title = {Linking Lexical and Corpus Data for Sign Languages: {NGT} {Signbank} and the {Corpus} {NGT}}, pages = {41--46}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16023.html}, abstract = {How can lexical resources for sign languages be integrated with corpus annotations? We answer this question by discussing an increasingly frequent scenario for sign language resources, where the lexical data are stored in an online lexical database that may also serve as a sign language dictionary, while the annotation data are offline files in the ELAN Annotation Format (EAF). There is by now broad consensus on the need for ID-glosses in corpus annotation, which in turn requires having at least a list of ID-glosses with a description of the phonological form and meaning of the signs. There is less of a consensus on standards for glossing, on practices of sign lemmatisation, and on the types of information that need to be stored in the lexical database. This paper contributes to the establishment of standards for sign language resources by discussing how two data resources for Sign Language of the Netherlands (NGT) are currently being integrated, using the ELAN annotation software for corpus annotation and an adaptation of the Auslan Signbank software as a lexical database. We discuss some of the present relations between two large NGT data sets, and outline some future developments that are foreseen.} } @inproceedings{demircioglu:16005:sign-lang:lrec, author = {Demircio{\u g}lu, Burcak and B{\"u}lb{\"u}l, G{\"u}ll{\"u} and K{\"o}se, Hatice}, title = {Recognition of Sign Language Hand Shape Primitives With {Leap} {Motion}}, pages = {47--52}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16005.html}, abstract = {In this study, a rule based heuristic method is proposed to recognize the primitive hand shapes of Turkish Sign Language (TID) which are sensed by a Leap Motion device. The hand shape data set was also tested with selected machine learning method (Random Forest), and the results of two approaches were compared. The proposed system required less data than the machine learning method, and its success rate was higher.} } @inproceedings{dilsizian:16031:sign-lang:lrec, author = {Dilsizian, Mark and Tang, Zhiqiang and Metaxas, Dimitris and Huenerfauth, Matt and Neidle, Carol}, title = {The Importance of {3D} Motion Trajectories for Computer-based Sign Recognition}, pages = {53--58}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16031.html}, abstract = {Computer-based sign language recognition from video is a challenging problem because of the spatiotemporal complexities inherent in sign production and the variations within and across signers. However, linguistic information can help constrain sign recognition to make it a more feasible classification problem. We have previously explored recognition of linguistically significant 3D hand configurations, as start and end handshapes represent one major component of signs; others include hand orientation, place of articulation in space, and movement. Thus, although recognition of handshapes (on one or both hands) at the start and end of a sign is essential for sign identification, it is not sufficient. Analysis of hand and arm movement trajectories can provide additional information critical for sign identification. In order to test the discriminative potential of the hand motion analysis, we performed sign recognition based exclusively on hand trajectories while holding the handshape constant. To facilitate this evaluation, we captured a collection of videos involving signs with a constant handshape produced by multiple subjects; and we automatically annotated the 3D motion trajectories. 3D hand locations are normalized in accordance with invariant properties of ASL movements. We trained time-series learning-based models for different signs of constant handshape in our dataset using the normalized 3D motion trajectories. Results show significant computer-based sign recognition accuracy across subjects and across a diverse set of signs. Our framework demonstrates the discriminative power and importance of 3D hand motion trajectories for sign recognition, given known handshapes.} } @inproceedings{ebling:16009:sign-lang:lrec, author = {Ebling, Sarah and Boyes Braem, Penny}, title = {Linking a Web Lexicon of {DSGS} Technical Signs to {iLex}}, pages = {59--62}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16009.html}, abstract = {A website for a lexicon of Swiss German Sign Language equivalents of technical terms was developed several years ago using Flash technology. In the intervening years, the backend research database was migrated from FileMaker to iLex. Here, we report on the development of a web platform that provides access to the same technical signs by extracting the relevant information directly from iLex. This new platform has many advantages: New sets of signs for technical terms can be added or existing ones modified in iLex at any time, and changes are reflected in the web platform upon refreshing the browser. Just as importantly, the new platform can now also be accessed through all major mobile operating systems, as it does not rely on Flash. We descri be how information on the glosses, keywords, videos of citation forms, status, and uses of the technical signs is represented in iLex and how the corresponding web platform was built.} } @inproceedings{efthimiou:16003:sign-lang:lrec, author = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Dimou, Athanasia-Lida and Goulas, Theodoros and Karioris, Panagiotis and Vasilaki, Kyriaki and Vacalopoulou, Anna and Pissaris, Michalis}, title = {From a Sign Lexical Database to an {SL} Golden Corpus -- the {POLYTROPON} {SL} Resource}, pages = {63--68}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16003.html}, abstract = {The POLYTROPON lexicon resource is being created in an attempt i) to gather and recapture already available lexical resources of Greek Sign Language (GSL) in an up-to-date homogeneous manner, ii) to enrich these resources with new lemmas, and iii) to end up with a multipurpose-multiuse resource which can be equally exploited in end user oriented educational/communication services and in supporting various SL technologies. The database that hosts the newly acquired resource, incorporates various SL oriented fields of information, including information on compounding, GSL synonyms, classifier qualities, lemma related senses, semantic groupings etc, and also lemma coding for their manual and non-manual articulation activity. It also provides linking of GSL and Modern Greek equivalent(s) lemma pairs to serve bilingual use purposes. A by-product of considerable value is the parallel corpus which derived from the GSL examples of use accompanying each lemma entry in the dictionary and their translations into Modern Greek. The annotation of the corpus for the entailed signs and assignment of respective glosses in combination with data capturing by both HD and Kinect cameras in three repetitions, allowed for the creation of a golden parallel corpus available to the community of SL technologies for experimentation with various approaches to SL recognition, MT and information retrieval.} } @inproceedings{filhol:16027:sign-lang:lrec, author = {Filhol, Michael and Hadjadj, Mohamed Nassime}, title = {Juxtaposition as a Form Feature - Syntax Captured and Explained rather than Assumed and Modelled}, pages = {69--74}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16027.html}, abstract = {In this article, we report on a study conducted to further the design a formal grammar model (AZee), confronting it to the traditional notion of syntax along the way. The model was initiated to work as an unambiguous linguistic input for signing avatars, accounting for all simultaneous articulators while doing away with the generally assumed and separate levels of lexicon, syntax, etc. Specifically, the work presented here focused on juxtaposition in signed streams (a fundamental feature of syntax), which we propose to consider as a mere form feature, and use it as the starting point of data-driven searches for grammatical rules. The result is a tremendous progress in coverage of LSF grammar, and fairly strong evidence that our initial goal is attainable. We give concrete examples of rules, and a clear illustration of the recursive mechanics of the grammar producing LSF forms, and conclude with theoretical remarks on the AZee paradigm in terms of syntax, word/sign order and the like.} } @inproceedings{fisher:16026:sign-lang:lrec, author = {Fisher, Jami N. and Hochgesang, Julie A. and Tamminga, Meredith}, title = {Examining Variation in the Absence of a 'Main' {ASL} Corpus: The Case of the Philadelphia Signs Project}, pages = {75--80}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16026.html}, abstract = {The Philadelphia Signs Project emerged from the community`s desire to document their local ASL variety, originating at the Pennsylvania School for the Deaf. This variety is anecdotally reported to be notably different from other ASL varieties. This project is founded upon the consistent observations of this marked difference. We aim to uncover what, if anything, makes the Philadelphia variety distinct from other varieties in the United States. \par Beyond some lexical items, it is unknown what linguistic features mark this variety as ``different.'' Comparison to other ASL varieties is difficult given the absence of a main and representative ASL corpus. This paper describes our sociolinguistic data collection methods, annotation procedures, and archiving approach. We summarize several preliminary observations about potentially dialect-specific features beyond the lexicon, such as unusual phonological alternations and word orders. Finally, we outline our plans to test these features with surveys for non-Philadelphians using Philadelphia lexical items, extending to more abstract phonological and syntactic features. This line of inquiry supplements our current archiving practices, facilitating comparison with a main corpus in the future. We maintain that even without a main corpus for comparison, it is essential to document a language variety when the community wishes to preserve it.} } @inproceedings{gabarrolopez:16010:sign-lang:lrec, author = {Gabarr{\'o}-L{\'o}pez, S{\'i}lvia and Meurant, Laurence}, title = {Slicing your {SL} data into Basic Discourse Units ({BDUs}). Adapting the {BDU} model (syntax + prosody) to Signed Discourse}, pages = {81--88}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16010.html}, abstract = {This paper aims to propose a model for the segmentation of signed discourse by adapting the Basic Discourse Units (BDU) Model. This model was conceived for spoken data and allows the segmentation of both monologues and dialogues. It consists of three steps: delimiting syntactic units on the basis of the Dependency Grammar (DG), delimiting prosodic units on the basis of a set of acoustic cues, and finding the convergence point between syntactic and prosodic units in order to establish BDUs. A corpus containing data from French Belgian Sign Language (LSFB) will be firstly segmented according to the principles of the DG. After establishing a set of visual cues equivalent to the acoustic ones, a prosodic segmentation will be carried out independently. Finally, the convergence points between syntactic and prosodic units will give rise to BDUs. The ultimate goal of adapting the BDU Model to the signed modality is not only to allow the study of the position of discourse markers (DMs) as in the original model, but also to give an answer to a controversial issue in SL research such as the segmentation of SL corpus data, for which a satisfactory solution has not been found so far.} } @inproceedings{hanke:16024:sign-lang:lrec, author = {Hanke, Thomas}, title = {Towards a Visual Sign Language Corpus Linguistics}, pages = {89--92}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16024.html}, abstract = {Visualisations have a long tradition in linguistics, as in many fields dealing with complex structure. New forms of representations have been introduced to Visual Linguistics in the recent past, e.g. to help the researcher find the needle in a haystack, i.e. corpus. Here we present visualisation services available in iLex making a combined corpus and lexical database visually accessible. While many approaches suggested for textual languages transfer to sign language data as well, others explore sign-specific structure, such as multi-dimensional concordances not being restricted to sequentiality. Experimental combinations of animated visualisation and image processing might support the researcher to compensate for incomplete high-quality (=manual) annotation. In the long run, we see the potential that visualisation and data manipulation go hand in hand, allowing future user interfaces that are less text-heavy than today's sign language annotation environments.} } @inproceedings{jantunen:16006:sign-lang:lrec, author = {Jantunen, Tommi and Pippuri, Outi and Wainio, Tuija and Puupponen, Anna and Laaksonen, Jorma}, title = {Annotated video corpus on {FinSL} with {Kinect} and computer-vision data}, pages = {93--100}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16006.html}, abstract = {This paper presents an annotated video corpus of Finnish Sign Language (FinSL) to which has been appended Kinect and computer-vision data. The video material consists of signed retellings of the stories Snowman and Frog, where are you?, elicited from 12 native FinSL signers in a dialogue setting. The recordings were carried out with 6 cameras directed toward the signers from different angles, and 6 signers were also recorded with one Kinect motion and depth sensing input device. All the material has been annotated in ELAN for signs, translations, grammar and prosody. To further facilitate research into FinSL prosody, computer-vision data describing the head movements and the aperture changes of the eyes and mouth of all the signers has been added to the corpus. The total duration of the material is 45 minutes and that part of it that is permitted by research consents is available for research purposes via the LAT online service of the Language Bank of Finland. The paper briefly demonstrates the linguistic use of the corpus.} } @inproceedings{jedlicka:16022:sign-lang:lrec, author = {Jedli{\v c}ka, Pavel and Kr{\v n}oul, Zden{\v e}k and {\v Z}elezn{\'y}, Milo{\v s}}, title = {Methods for Recognizing Interesting Events within Sign Language Motion Capture Data}, pages = {101--104}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16022.html}, abstract = {Rising popularity of motion capture in movie-production makes this technology more robust and more accessible. Utilization of this technology for sign language capturing and analysis is evident. The article deals with the usability of the motion capture in creating sign language corpora. A large amount of the data acquired by the motion capture has to be processed to provide usable data for wide range of research areas: e.g. sign language recognition, translation, synthesis, linguistics, etc. The aim of this article is to explore possible methods to detect interesting events in data using machine learning techniques. The result is a method for detection of the beginning and the end of the sign, hand location, finger and palm orientation, whether the sign is one or two handed, and symmetry in the two-handed signs.} } @inproceedings{kacorri:16007:sign-lang:lrec, author = {Kacorri, Hernisa and Syed, Ali Raza and Huenerfauth, Matt and Neidle, Carol}, title = {Centroid-Based Exemplar Selection of {ASL} Non-Manual Expressions using Multidimensional Dynamic Time Warping and {MPEG4} Features}, pages = {105--110}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16007.html}, abstract = {We investigate a method for selecting recordings of human face and head movements from a sign language corpus to serve as a basis for generating animations of novel sentences of American Sign Language (ASL). Drawing from a collection of recordings that have been categorized into various types of non-manual expressions (NMEs), we define a method for selecting an exemplar recording of a given type using a centroid-based selection procedure, using multivariate dynamic time warping (DTW) as the distance function. Through intra- and inter-signer methods of evaluation, we demonstrate the efficacy of this technique, and we note useful potential for the DTW visualizations generated in this study for linguistic researchers collecting and analyzing sign language corpora.} } @inproceedings{keranen:16016:sign-lang:lrec, author = {Ker{\"a}nen, Jarkko and Syrj{\"a}l{\"a}, Henna and Salonen, Juhana and Takkinen, Ritva}, title = {The Usability of the Annotation}, pages = {111--116}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16016.html}, abstract = {Several corpus projects for sign languages have tried to establish conventions and standards for the annotation of signed data. When discussing corpora, it is necessary to develop a way of considering and evaluating holistically the features and problems of annotation. This paper aims to develop a conceptual framework for the evaluation of the usability of annotations. The purpose of the framework is not to give conventions for annotating but to offer tools for the evaluation of the usability of the annotation, in order to make annotations more usable and make it possible to justify and explain decisions about annotation conventions. Based on our experience of annotation in the corpus project of Finland`s Sign Languages (CFINSL), we have developed six principles for the evaluation of annotation. In this article, using these six principles, we evaluate the usability of the annotations in CFINSL and other corpus projects. The principles have offered benefits in CFINSL: we are able to evaluate our annotations more systematically and holistically than ever before. Our work can be seen as an effort to bring a framework of usability to corpus work.} } @inproceedings{kimmelman:16018:sign-lang:lrec, author = {Kimmelman, Vadim}, title = {Transitivity in {RSL}: a corpus-based account}, pages = {117--120}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16018.html}, abstract = {A recent typological study of transitivity Haspelmath (2015) demonstrated that verbs can be ranked according to transitivity prominence, that is, according to how likely they are to be transitive cross-linguistically. This ranking can be argued to be cognitively rooted (based on the properties of the events and their participants) or frequency-related (based on the frequency of different types of events in the real world). Both types of explanation imply that the transitivity ranking should apply across modalities. To test it, we analysed transitivity of frequent verbs in the corpus of Russian Sign Language by calculating the proportion of overt direct and indirect objects and clausal complements. We found that transitivity as expressed by the proportion of overt direct objects is highly positively correlated with the transitive prominence determined cross-linguistically. We thus confirmed the modality-independent nature of transitivity ranking.} } @inproceedings{koller:16036:sign-lang:lrec, author = {Koller, Oscar and Ney, Hermann and Bowden, Richard}, title = {Automatic Alignment of {HamNoSys} Subunits for Continuous Sign Language Recognition}, pages = {121--128}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16036.html}, abstract = {This work presents our recent advances in the field of automatic processing of sign language corpora targeting continuous sign language recognition. We demonstrate how generic annotations at the articulator level, such as HamNoSys, can be exploited to learn subunit classifiers. Specifically, we explore cross-language-subunits of the hand orientation modality, which are trained on isolated signs of publicly available lexicon data sets for Swiss German and Danish sign language and are applied to continuous sign language recognition of the challenging RWTH-PHOENIX-Weather corpus featuring German sign language. We observe a significant reduction in word error rate using this method.} } @inproceedings{kozuh:16019:sign-lang:lrec, author = {Kozuh, Ines and Kosec, Primo{\v z} and Debevc, Matja{\v z}}, title = {Evaluating User Experience of the Online Dictionary of the {Slovenian} {Sign} {Language}}, pages = {129--132}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16019.html}, abstract = {The extensive use of mobile devices and tablets has resulted in an increasing need for the ubiquitous availability of different types of dictionaries online. The purpose of our study was to evaluate the user experience and usability of the online dictionary of the Slovenian sign language. Six Slovenian hearing non-signers were included in the study. While using the online dictionary, participants were asked to complete six tasks: searching for a letter, a word, written explanation of the word, thematic section and particular fairy tale, as well as completing the quiz. In addition, the participants evaluated the usability of the online dictionary with the System Usability Scale. The findings revealed that participants perceived the tasks ``searching for the word'' and ``searching for the thematic section'' to be the most difficult tasks and ``completing the quiz'' to be the easiest one. Regarding the time measured, the task ``searching for the word'' was the most time-consuming and the task ``searching for the letter'' was the least. This study provides insights into how Slovenian hearing users perceive using the online dictionary of the Slovenian sign language and could be the basis for future research with users of Slovenian sign language.} } @inproceedings{krnoul:16020:sign-lang:lrec, author = {Kr{\v n}oul, Zden{\v e}k and Kanis, Jakub and {\v Z}elezn{\'y}, Milo{\v s} and M{\"u}ller, Lud{\v e}k}, title = {Semiautomatic Data Glove Calibration for Sign Language Corpora Building}, pages = {133--136}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16020.html}, abstract = {The article deals with a recording procedure for sign language dataset building mainly for avatar synthesis systems. Combined data glove and optical capture technique is considered. We present initial experiences with the motion capture data produced by the CyberGlove3 gloves and a set of new tools to ease the recording process, glove calibration and proper interpretation by the 3D model. It results in a more flexible solution for the sign language capture integrating manual glove calibration with an automatic initialization, time synchronization and high-resolution sensor readings.} } @inproceedings{langer:16013:sign-lang:lrec, author = {Langer, Gabriele and Hanke, Thomas and Konrad, Reiner and K{\"o}nig, Susanne}, title = {``Non-tokens'': When Tokens Should not Count as Evidence of Sign Use}, pages = {137--142}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16013.html}, abstract = {Lemmatised corpora consist of tokens as instantiations of signs (types). Tokens usually count as evidences of the signs' use. Frequency of tokens is an important criterion for the lexical status of a sign. In combination with metadata on the signers' sociolinguistic backgrounds such as age, gender, and origin these tokens can also be analysed for regional and sociolinguistic variation. However, corpora may also contain instances of sign use that do not reflect the sign use of the person uttering them. This is particularly true for metalinguistic discussions of signs, malformed signing and slips of the hand as well as other phenomena such as copying/repeating signs of the interlocutors or from stimulus material. In our presentation we list and discuss different kinds of sign use (tokens) that should either not be counted as proof of a sign type at all or at least not as evidence of regular sign use by that particular person. Examples of these ``non-tokens'' are either taken from the DGS Corpus or from uploaded video answers of the DGS Feedback. We also discuss some implications on how to annotate these cases.} } @inproceedings{langer:16014:sign-lang:lrec, author = {Langer, Gabriele and Troelsg{\aa}rd, Thomas and Kristoffersen, Jette and Konrad, Reiner and Hanke, Thomas and K{\"o}nig, Susanne}, title = {Designing a Lexical Database for a Combined Use of Corpus Annotation and Dictionary Editing}, pages = {143--152}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16014.html}, abstract = {In a combined corpus-dictionary project, you would need one lexical database that could serve as a shared ``backbone'' for both corpus annotation and dictionary editing, but it is not that easy to define a database structure that applies satisfactorily to both these purposes. In this paper, we will exemplify the problem and present ideas on how to model structures in a lexical database that facilitate corpus annotation as well as dictionary editing. The paper is a joint work between the DGS Corpus Project and the DTS Dictionary Project. The two projects come from opposite sides of the spectrum (one adjusting a lexical database grown from dictionary making for corpus annotating, one building a lexical database in parallel with corpus annotation and editing a corpus-based dictionary), and we will consider requirements and feasible structures for a database that can serve both corpus and dictionary.} } @inproceedings{mcdonald:16001:sign-lang:lrec, author = {McDonald, John C. and Wolfe, Rosalee and Wilbur, Ronnie and Moncrief, Robyn and Malaia, Evie A. and Fujimoto, Sayuri and Baowidan, Souad and Stec, Jessika}, title = {A New Tool to Facilitate Prosodic Analysis of Motion Capture Data and a Datadriven Technique for the Improvement of Avatar Motion}, pages = {153--158}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16001.html}, abstract = {Researchers have been investigating the potential rewards of utilizing motion capture for linguistic analysis, but have encountered challenges when processing it. A significant problem is the nature of the data: along with the signal produced by the signer, it also contains noise. The first part of this paper is an exposition on the origins of noise and its relationship to motion capture data of signed utterances. The second part presents a tool, based on established mathematical principles, for removing or isolating noise to facilitate prosodic analysis. This tool yields surprising insights into a data-driven strategy for a parsimonious model of life-like appearance in a sparse key-frame avatar.} } @inproceedings{meurant:16032:sign-lang:lrec, author = {Meurant, Laurence and Cleve, Anthony and Crasborn, Onno}, title = {Using sign language corpora as bilingual corpora for data mining: Contrastive linguistics and computer-assisted annotation}, pages = {159--166}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16032.html}, abstract = {More and more sign languages nowadays are now documented by large-scale digital corpora. But exploiting sign language (SL) corpus data remains subject to the time consuming and expensive manual task of annotating. In this paper, we present an ongoing research that aims at testing a new approach to better mine SL data. It relies on the methodology of corpus-based contrastive linguistics, exploiting SL corpora as bilingual corpora. We present and illustrate the main improvements we foresee in developing such an approach: downstream, for the benefit of the linguistic description and the bilingual (signed - spoken) competence of teachers, learners and the users; and upstream, in order to enable the automatisation of the annotation process of sign language data. We also describe the methodology we are using to develop a concordancer able to turn SL corpora into searchable translation corpora, and to derive from it a tool support to annotation.} } @inproceedings{meurant:16030:sign-lang:lrec, author = {Meurant, Laurence and Sinte, Aur{\'e}lie and Bernagou, Eric}, title = {The {French} {Belgian} {Sign} {Language} Corpus. A User-Friendly Corpus Searchable Online}, pages = {167--174}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16030.html}, abstract = {This paper presents the first large-scale corpus of French Belgian Sign Language (LSFB) available via an open access website (www.corpus-lsfb.be). Visitors can search within the data and the metadata. Various tools allow the users to find sign language video clips by searching through the annotations and the lexical database, and to filter the data by signer, by region, by task or by keyword. The website includes a lexicon linked to an online LSFB dictionary.} } @inproceedings{pigou:16011:sign-lang:lrec, author = {Pigou, Lionel and Van Herreweghe, Mieke and Dambre, Joni}, title = {Sign Classification in Sign Language Corpora with Deep Neural Networks}, pages = {175--178}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16011.html}, abstract = {Automatic and unconstrained sign language recognition (SLR) in image sequences remains a challenging problem. The variety of signers, backgrounds, sign executions and signer positions makes the development of SLR systems very challenging. Current methods try to alleviate this complexity by extracting engineered features to detect hand shapes, hand trajectories and facial expressions as an intermediate step for SLR. Our goal is to approach SLR based on feature learning rather than feature engineering. We tackle SLR using the recent advances in the domain of deep learning with deep neural networks. The problem is approached by classifying isolated signs from the Corpus VGT (Flemish Sign Language Corpus) and the Corpus NGT (Dutch Sign Language Corpus). Furthermore, we investigate cross-domain feature learning to boost the performance to cope with the fewer Corpus VGT annotations.} } @inproceedings{salonen:16017:sign-lang:lrec, author = {Salonen, Juhana and Takkinen, Ritva and Puupponen, Anna and Nieminen, Henri and Pippuri, Outi}, title = {Creating Corpora of {Finland}'s Sign Languages}, pages = {179--184}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16017.html}, abstract = {This paper discusses the process of creating corpora of the sign languages used in Finland, Finnish Sign Language (FinSL) and Finland-Swedish Sign Language (FinSSL). It describes the process of getting informants and data, editing and storing the data, the general principles of annotation, and the creation of a web-based lexical database, the FinSL Signbank, developed on the basis of the NGT Signbank, which is a branch of the Auslan Signbank. The corpus project of Finland{\' }s Sign Languages (CFINSL) started in 2014 at the Sign Language Centre of the University of Jyv{\"a}skyl{\"a}. Its aim is to collect conversations and narrations from 80 FinSL users and 20 FinSSL users who are living in different parts of Finland. The participants are filmed in signing sessions led by a native signer in the Audio-visual Research Centre at the University of Jyv{\"a}skyl{\"a}. The edited material is stored in the IDA storage service produced by the CSC -- IT Center for Science, and the metadata will be saved into CMDI metadata. Every informant is asked to sign a consent form where they state for what kinds of purposes their signing can be used. The corpus data are annotated using the ELAN tool. At the moment, annotations are created on the levels of glosses and translation.} } @inproceedings{soudi:16033:sign-lang:lrec, author = {Soudi, Abdelhadi and Vinopol, Corinne}, title = {A Digital {Moroccan} {Sign} {Language} {STEM} Thesaurus}, pages = {185--190}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16033.html}, abstract = {This paper presents a gesture-based linguistic approach to assisting Moroccan Sign Language (MSL) users in understanding and appropriately using Science, Technology, Engineering and Mathematics (STEM) terminology by creating the first-ever digital MSL STEM Thesaurus. The thesaurus enables Deaf individuals to describe signs and obtain Standard Arabic word equivalents, concept graphics, and definitions in both MSL and Arabic. This is accomplished not only by providing words comparable to signs that they know, but also by providing other information (e.g., signed definitions) that helps differentiate Arabic word choices. The thesaurus is supported by a Concordancer for better illustration and disambiguation of STEM terms. The thesaurus will likely prove to be an invaluable tool that will enable children and adults who rely on MSL for communication, both deaf and otherwise communication impaired, to better understand and write knowledgeably and clearly on STEM topics, and pass standardized assessments.} } @inproceedings{vintar:16012:sign-lang:lrec, author = {Vintar, {\v S}pela and Jerko, Bo{\v s}tjan}, title = {Online Concordancer for the {Slovene} {Sign} {Language} Corpus {SIGNOR}}, pages = {191--194}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16012.html}, abstract = {We present the first version of an online concordancing tool for the Slovene Sign Language SIGNOR corpus. The corpus search tool allows querying the SIGNOR annotated database by glosses and displays the hits in a keyword-in-context (KWIC) format, accompanied by frequency information, HamNoSys transcription and metadata. The main purpose of the tool is linguistic research, more specifically sign language lexicography, but also providing general public access to the corpus.} } @proceedings{lrec:sign-lang:14, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, title = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, url = {http://www.lrec-conf.org/proceedings/lrec2014/workshops/LREC2014Workshop-SignLanguage%20Proceedings.pdf} } @inproceedings{balvet:14030:sign-lang:lrec, author = {Balvet, Antonio and Sallandre, Marie-Anne}, title = {Mouth features as non-manual cues for the categorization of lexical and productive signs in {French} {Sign} {Language} ({LSF})}, pages = {1--6}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14030.html}, abstract = {In this paper, we present evidence from a case study in LSF, conducted on narratives from 6 adult signers. In this study, picture and video stimuli have been used in order to identify the role of non-manual features such as gaze, facial expressions and mouth features. We discuss the importance of mouth features as markers of the alternation between frozen (Lexical Units, LU) and productive signs (Highly Iconic Structures, HIS). Based on qualitative and quantitative analysis, we propose to consider mouth features, i.e. mouthings on the one hand, and mouth gestures on the other hand, as markers, respectively, of Lexical Units versus Highly Iconic Structures. As such, we propose to consider mouthings and mouth gestures as fundamental cues for determining the nature, role and interpretation of manual signs, in conjunction with other non-manual features (facial expression). We propose an ELAN annotation template for mouth features in SLs, and a discussion on the different mouth features and their respective roles as discourse and syntactic-semantic operators.} } @inproceedings{borstell:14023:sign-lang:lrec, author = {B{\"o}rstell, Carl and Mesch, Johanna and Wallin, Lars}, title = {Segmenting the {Swedish} {Sign} {Language} corpus: On the possibilities of using visual cues as a basis for syntactic segmentation}, pages = {7--10}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14023.html}, abstract = {This paper deals with the possibility of conducting syntactic segmentation of the Swedish Sign Language Corpus (SSLC) on the basis of the visual cues from both manual and nonmanual signals. The SSLC currently features segmentation on the lexical level only, which is why the need for a linguistically valid segmentation on e.g.~the clausal level would be very useful for corpus-based studies on the grammatical structure of Swedish Sign Language (SSL). An experiment was carried out letting seven Deaf signers of SSL each segment two short texts (one narrative and one dialogue) using ELAN, based on the visual cues they perceived as boundaries. This was later compared to the linguistic analysis done by a language expert (also a Deaf signer of SSL), who segmented the same texts into what was considered syntactic clausal units. Furthermore, these segmentation procedures were compared to the segmentation done for the Swedish translations also found in the SSLC. The results show that though the visual and syntactic segmentations overlap in many cases, especially when a number of cues coincide, the visual segmentation is not consistent enough to be used as a means of segmenting syntactic units in the SSLC.} } @inproceedings{bouzid:14008:sign-lang:lrec, author = {Bouzid, Yosra}, title = {Synthesizing facial expressions for sign language avatars}, pages = {11--18}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14008.html}, abstract = {Sign language is more than just moving the fingers or hands; it is a visual language in which non manual gestures play a very important role. Recently, a growing body of research has paid increasing attention to the development of signing avatars endowed with a set of facial expressions in order to perform the actual functioning of the sign language, and gain wider acceptance by deaf users. In this paper, we propose an effective method to generate facial expressions for signing avatars basing on the physics-based muscle model. The main focus of our work is to automate the task of the muscle mapping on the face model in the correct anatomical positions and the detection of the jaw part by using a small set of MPEG-4 Feature Points of the given mesh.} } @inproceedings{braffort:14028:sign-lang:lrec, author = {Braffort, Annelies}, title = {Eye gaze annotation practices: Description vs. interpretation}, pages = {19--22}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14028.html}, abstract = {If sharing best practices and conventions for annotation of Sign Language corpora is a growing activity, less attention has been given to the annotation of non-manual activity. This paper focuses on annotation of eye gaze. The aim is to report some of the practices, and begin a discussion on this topic, to be continued during the workshop. After having presented and discussed the nature of the annotation values in several projects, and explain our own practices, we examine the level of interpretation in the annotation process, and how the design of annotation conventions can be motivated by limitations in the available annotation tools.} } @inproceedings{crasborn:14034:sign-lang:lrec, author = {Crasborn, Onno and Bank, Richard}, title = {An annotation scheme for mouth actions in sign languages}, pages = {23--28}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14034.html}, abstract = {This paper describes the annotation scheme that has been used for research on mouth actions in the Corpus NGT. An orthographic representation of the visible part of the mouthing is supplemented by the citation form of the word, a categorisation of the type of the mouth action, the number of syllables in the mouth action, (non)alignment of a corresponding sign, and a layer representing some special functions. The scheme has been used for a series of studies on Sign Language of the Netherlands. The structure and vocabularies for the annotation scheme are described, as well as the experiences in its use so far. Annotations will be published in the second release of the Corpus NGT annotations in late 2014.} } @inproceedings{curiel:14007:sign-lang:lrec, author = {Curiel, Arturo and Collet, Christophe}, title = {Implementation of an automatic sign language lexical annotation framework based on propositional dynamic logic}, pages = {29--36}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14007.html}, abstract = {In this paper, we present the implementation of an automatic Sign Language (SL) sign annotation framework based on a formal logic, the Propositional Dynamic Logic (PDL). Our system relies heavily on the use of a specific variant of PDL, the Propositional Dynamic Logic for Sign Language (PDLSL), which lets us describe SL signs as formulae and corpora videos as labeled transition systems (LTSs). Here, we intend to show how a generic annotation system can be constructed upon these underlying theoretical principles, regardless of the tracking technologies available or the input format of corpora. With this in mind, we generated a development framework that adapts the system to specific use cases. Furthermore, we present some results obtained by our application when adapted to one distinct case, 2D corpora analysis with pre-processed tracking information. We also present some insights on how such a technology can be used to analyze 3D real-time data, captured with a depth device.} } @inproceedings{dimou:14022:sign-lang:lrec, author = {Dimou, Athanasia-Lida and Goulas, Theodoros and Efthimiou, Eleni and Fotinea, Stavroula-Evita}, title = {Creation of a multipurpose sign language lexical resource: The {GSL} lexicon database}, pages = {37--42}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14022.html}, abstract = {The GSL lexicon database is the first extensive database of Greek Sign Language (GSL) signs, created on the basis of knowledge derived from the linguistic analysis of natural signers{\'i} data. It incorporates a lemma list that currently includes approximately 6,000 entries and is intended to reach a total number of 10,000 entries within the next two years. The design of the database allows for classification of signs on the basis of their articulation features as regards both manual and non-manual elements. The adopted information management schema accompanying each entry provides for retrieval according to a variety of linguistic properties. In parallel, annotation of the full set of sign articulation features feeds more natural performance of synthetic signing engines and more effective treatment of sign language (SL) data in the framework of sign recognition and natural language processing.} } @inproceedings{dubot:14006:sign-lang:lrec, author = {Dubot, R{\'e}mi and Collet, Christophe}, title = {A hybrid formalism to parse sign languages}, pages = {43--48}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14006.html}, abstract = {Sign Language (SL) linguistic is dependent on the expensive task of annotating. Some automation is already available for low-level information (eg. body part tracking) and the lexical level has shown significant progresses. The syntactic level lacks annotated corpora as well as complete and consistent models. This article presents a solution for the automatic annotation of SL syntactic elements. It exposes a formalism able to represent both constituency-based and dependency-based models. The first enables the representation of structures one may want to annotate, the second aims at fulfilling the holes of the first. A parser is presented and used to conduct two experiments on the solution. One experiment is on a real corpus, the other is on a synthetic corpus.} } @inproceedings{filhol:14012:sign-lang:lrec, author = {Filhol, Michael and Hadjadj, Mohamed Nassime and Choisier, Annick}, title = {Non-manual features: The right to indifference}, pages = {49--54}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14012.html}, abstract = {This paper discusses the way sign language can be described with a global account of the visual channel, not separating manual articulators in any way. In a first section section it shows that non-manuals are often either ignored in favour of manual focus, or included but given roles that are mostly different from the mainly hand-assigned lexical role. A second section describes the AZee model as a tool to describe Sign Language productions without assuming any separation, neither between articulators nor between grammatical roles. We conclude by giving a full AZee description for one of the several examples populating the paper.} } @inproceedings{gabarrolopez:14018:sign-lang:lrec, author = {Gabarr{\'o}-L{\'o}pez, S{\'i}lvia and Meurant, Laurence}, title = {When nonmanuals meet semantics and syntax: Towards a practical guide for the segmentation of sign language discourse}, pages = {55--62}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14018.html}, abstract = {This paper aims to contribute to the segmentation of sign language (SL) discourses by providing an operational synthesis of the criteria that signers use to segment a SL discourse. Such procedure was required when it came to analyse the role of buoys as discourse markers (DMs), which is part of a PhD on DMs in French Belgian SL (LSFB). All buoy markers found in the data had to be differentiated in terms of scope: some markers (like most list buoy markers) seemed to be long range markers, whereas others (like most fragment buoy markers) seemed to have a local scope only. Our practical guide results from a hierarchized and operationalized synthesis of the criteria, which explain the segmentation judgments of deaf (native and non-native) and hearing (non-native) signers of LSFB who were asked to segment a small-scale (1h) corpus. These criteria are a combination of non-manual, semantic and syntactic cues. Our contribution aims to be shared, tested on other SLs and hopefully improved to provide SL researchers who conduct discourse studies with some efficient and easy-to-use guidelines, and avoid them extensive (and time-consuming) annotation of the manual and non-manual cues that are related to the marking of boundaries in SLs.} } @inproceedings{geraci:14017:sign-lang:lrec, author = {Geraci, Carlo and Mazzei, Alessandro}, title = {Last train to ``{Rebaudengo} {Fossano}'': The case of some names in avatar translation}, pages = {63--66}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14017.html}, abstract = {In this study, we present an unorthodox case study where cross-linguistic and cross modal information is provided by a ``non-manual'' channel during the process of automatic translation from spoken into sign language (SL) via virtual actors (avatars). Specifically, we blended written forms (crucially, not subtitles) into the sign stream in order to import the names of less-known train stations into Italian Sign Language (LIS). This written Italian-LIS blending is a more effective compromise for Deaf passengers than fully native solutions like fingerspelling or using the local less-known SL names. We report here on part of an ongoing project, LIS4ALL, aiming at producing a prototype avatar signing train station announcements. The final product will be exhibited at the train station of Torino Porta Nuova in Turin, Italy.} } @inproceedings{hanke:14029:sign-lang:lrec, author = {Hanke, Thomas}, title = {Annotation of mouth activities with {iLex}}, pages = {67--70}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14029.html}, abstract = {Recordings from the DGS-Korpus project with 330 informants confirm that at least for German Sign Language (DGS) you hardly find longer stretches of signing not accompanied by any mouth activity. Independent of whether you consider mouth activity while signing as part of the sign language proper or as a parallel system interacting with sign language to jointly transport meaning, mouth activity is part of the linguistic system used by signers and should be treated as such by any corpus approach. In a purely bottom-up approach an annotation practice used for mouth activities would try to describe the phenomena and leave it to a second step to classify (e.g. between mouthing and mouth gestures) and relate (e.g. to spoken language words). For practical reasons, however, the first step is often skipped, and separate coding systems are applied to what is categorised either as mouthing derived from spoken language or mouth gesture where there is no obvious connection between the meaning expressed and any spoken language words expressing that same meaning. This happens not only for time (=budget) reasons, but also because it is difficult for coders to describe mouth visemes precisely if the sign/mouth combo already suggests what is to be seen on the mouth. While there are established coding procedures to avoid influence as far as possible (like only showing the signer's face, provided video quality is good enough), they make the approach very time-consuming, even if not counting quality assurance measures like inter-transcriber agreement. Some projects undertaken at the IDGS in Hamburg therefore leave it with a spoken-language-driven approach: The mouth activity is classified as either mouth gesture or mouthing, and in the latter case the German word is noted down that a competent DGS signer ``reads'' from the lips, i.e. that word from the set of words to be expected with the co-temporal sign in its context that matches the observation. Standard orthography is used unless there is a substantial deviation. For mouth gestures, holistic labels are used. These two extremes span a whole spectrum of coding approaches that can be used for mouth activities. iLex, the Hamburg sign language annotation workbench, tries to support the whole range of solutions as good as possible. The poster w/ demo shows a variety of approaches actually in use or on the horizon and what iLex has to offer for each of those, from more time-series like systems to those evaluating co-occurrence and semantic relatedness, from novice-friendly decision trees to expert-only modes. Inter-transcriber agreement data on the examples given clearly show that a thorough analysis of data quality has to go beyond such measures.} } @inproceedings{huenerfauth:14010:sign-lang:lrec, author = {Huenerfauth, Matt and Kacorri, Hernisa}, title = {Release of Experimental stimuli and questions for evaluating facial expressions in animations of {American} {Sign} {Language}}, pages = {71--76}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14010.html}, abstract = {We have developed a collection of stimuli (with accompanying comprehension questions and subjective-evaluation questions) that can be used to evaluate the perception and understanding of facial expressions in ASL animations or videos. The stimuli have been designed as part of our laboratory's on-going research on synthesizing ASL facial expressions such as Topic, Negation, Yes/No Questions, WH-questions, and RH-questions. This paper announces the release of this resource, describes the collection and its creation, and provides sufficient details to enable researchers determine if it would benefit their work. Using this collection of stimuli and questions, we are seeking to evaluate computational models of ASL animations with linguistically meaningful facial expressions, which have accessibility applications for deaf users.} } @inproceedings{jayaprakash:14024:sign-lang:lrec, author = {Jayaprakash, Rekha and Hanke, Thomas}, title = {How to use depth sensors in sign language corpus recordings}, pages = {77--80}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14024.html}, abstract = {Recently, combined camera and depth sensor devices caused substantial advances in Computer Vision directly applicable to automatic coding a signer{\'i}s use of head movement, eye gaze, and, to some extent, facial expression. Automatic and even semi-automatic annotation of nonmanuals would mean dramatic savings on annotation time and are therefore of high interest for anyone working on sign language corpora. Optimally, these devices need to be placed directly in front of the signer{\'i}s face at a distance of less than 1m. While this might be ok for some experimental setups, it is definitely nothing to be used in a corpus setting for at least two reasons: (i) The signer looks at the device instead of into the eyes of an interlocutor. (ii) The device is in the field of view of other cameras used to record the signer{\'i}s manual and nonmanual behaviour. Here we report on experiments determining the degradation in performance when moving the devices away from their optimal positions in order to achieve a recording setup acceptable in a corpus context. For these experiments, we used two different device types (Kinect and Carmine 1.09) in combination with one mature CV software package specialised on face recognition (FaceShift). We speculate about the reasons for the asymmetries detected and how they could be resolved. We then apply the results to the studio setting used in the DGS Corpus project and show how the signers and cameras fields of view are influenced by introducing the new devices and are happy to discuss the acceptability of this approach.} } @inproceedings{johnston:14003:sign-lang:lrec, author = {Johnston, Trevor and van Roekel, Jane}, title = {Mouth-based non-manual coding schema used in the {Auslan} corpus: Explanation, application and preliminary results}, pages = {81--88}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14003.html}, abstract = {We describe a corpus-based study of one type of non-manual in signed languages (SLs) --- mouth actions. Our ultimate aim is to examine the distribution and characteristics of mouth actions in Auslan (Australian Sign Language) to gauge the degree of language-specific conventionalization of these forms. We divide mouth gestures into categories broadly based on Crasborn et al. (2008), but modified to accommodate our experiences with the Auslan data. All signs and all mouth actions are examined and the state of the mouth in each sign is assigned to one of three broad categories: (i) mouthings, (ii) mouth gestures, and (iii) no mouth action. Mouth actions that invariably occur while communicating in SLs have posed a number of questions for linguists: which are `merely borrowings' from the relevant ambient spoken language (SpL)? which are gestural and shared with all of the members of the wider community in which signers find themselves? and which are conventionalized aspects of the grammar of some or all SLs? We believe these schema captures all the relevant information about mouth forms and their use and meaning in context to enable us to describe their function and degree of conventionality.} } @inproceedings{koller:14031:sign-lang:lrec, author = {Koller, Oscar and Ney, Hermann and Bowden, Richard}, title = {Weakly supervised automatic transcription of mouthings for gloss-based sign language corpora}, pages = {89--94}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14031.html}, abstract = {In this work we propose a method to automatically annotate mouthings in sign language corpora, requiring no more than a simple gloss annotation and a source of weak supervision, such as automatic speech transcripts. For a long time, research on automatic recognition of sign language has focused on the manual components. However, a full understanding of sign language is not possible without exploring its remaining parameters. Mouthings provide important information to disambiguate homophones with respect to the manuals. Nevertheless most corpora for pattern recognition purposes are lacking any mouthing annotations. To our knowledge no previous work exists that automatically annotates mouthings in the context of sign language. Our method produces a frame error rate of 39{\%} for a single signer.} } @inproceedings{kubus:14026:sign-lang:lrec, author = {Kubu{\c s}, Okan}, title = {Discourse-based annotation of relative clause constructions in {Turkish} {Sign} {Language} ({TID}): A case study}, pages = {95--99}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14026.html}, abstract = {The functions of relative clause constructions (RCC) should be ideally analyzed at the discourse level, since the occurrence of RCCs can be explained by looking at interlocutors' use of grammatical and intonational means (cf. Fox and Thompson, 1990). To date, RCCs in sign language have been analyzed at the syntactic level with a special focus on cross-linguistic comparisons (see e.g. Pfau and Steinbach, 2005; Branchini and Donati, 2009). However, to our knowledge, there is no systematic corpus-based analysis of RCCs in sign languages so far. Since the elements of RCCs are mostly non-manual markers, it is often unclear how to capture and tag these elements together with the functions of RCCs. This question is discussed in light of corpus-based data from Turkish Sign Language. Following Biber et al. (2007), the corpus-based analysis of RCCs in TID follows the ``top-down'' approach. In spite of modality-specific issues, the steps in the process of annotation and identification of RCCs in TID fairly resemble this approach. The advantage of using these multiple steps is that the procedure not only captures the discourse functions of the RCCs but also identifies different strategies for creating RCCs based on linguistic forms.} } @inproceedings{lackner:14005:sign-lang:lrec, author = {Lackner, Andrea and Riemer Kankkonen, Nikolaus}, title = {Signing thoughts! A methodological approach within the semantic field work used for coding nonmanuals which express modality in {Austrian} {Sign} {Language} ({{\"O}GS})}, pages = {100--104}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14005.html}, abstract = {Signing thoughts gives the possibility to express unreal situations, possibilities and so forth. Also, signers may express their attitude on these thoughts such as being uncertain about an imagined situation. We describe a methodological approach within the semantic field work which was used for identifying nonmanuals in Austrian Sign Language (÷GS) which tend to occur in thoughts and which may code (epistemic and deontic) modality. First, the process of recording short stories which very likely include lines of thoughts is shown. Second, the annotation process and the outcome of this process is described. The findings show that in almost all cases the different annotators identified the same non-manual movements/positions and the same starting and ending points of these nonmanuals in association with the lexical entries. The direction of motion was distinguished by a contrast of movement. Some nonmanuals were distinguished due to intensified performance, size of performance, speed of performance, an additional movement component, or additional body tension. Finally, we present nonmanuals which frequently occur in signed thoughts. These include various epistemic markers, a deontic marker, indicators which show the hypothetical nature of signed thoughts, and an interrogative marker which is different to interrogative markers in direct questions.} } @inproceedings{luzardo:14021:sign-lang:lrec, author = {Luzardo, Marcos and Viitaniemi, Ville and Karppa, Matti and Laaksonen, Jorma and Jantunen, Tommi}, title = {Estimating head pose and state of facial elements for sign language video}, pages = {105--112}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14021.html}, abstract = {In this work we present methods for automatic estimation of non-manual gestures in sign language videos. More specifically, we study the estimation of three head pose angles (yaw, pitch, roll) and the state of facial elements (eyebrow position, eye openness, and mouth state). This kind of estimation facilitates automatic annotation of sign language videos and promotes more prolific production of annotated sign language corpora. The proposed estimation methods are incorporated in our publicly available SLMotion software package for sign language video processing and analysis. Our method implements a model-based approach: for head pose we employ facial landmarks and skins masks as features, and estimate yaw and pitch angles by regression and roll using a geometric measure; for the state of facial elements we use the geometric information of facial elements of the face as features, and estimate quantized states using a classification algorithm. We evaluate the results of our proposed methods in quantitative and qualitative experiments.} } @inproceedings{mantovan:14016:sign-lang:lrec, author = {Mantovan, Lara and Geraci, Carlo and Cardinaletti, Anna}, title = {Addressing the cardinals puzzle: New insights from non-nanual markers in {Italian} {Sign} {Language}}, pages = {113--116}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14016.html}, abstract = {This paper aims at investigating the main linguistic properties associated with cardinal numerals in LIS (Italian sign language). Considering this issue from several perspectives (phonology, prosody, semantics and syntax), we discuss some relevant corpus and elicited data with the purpose of shedding light on the distribution of cardinals in LIS. We also explain what triggers the emergence of different word/sign orders in the noun phrase. Non-manual markers are crucial in detecting two particular subcases.} } @inproceedings{mcdonald:14019:sign-lang:lrec, author = {McDonald, John C. and Wolfe, Rosalee and Moncrief, Robyn and Baowidan, Souad}, title = {Analysis for synthesis: Investigating corpora for supporting the automatic generation of role shift}, pages = {117--122}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14019.html}, abstract = {In signed languages, role shift is a process that can facilitate the description of statements, actions or thoughts of someone other than the person who is signing, and sign synthesis systems must be able to automatically create animations that portray it effectively. Animation is only as good as the data used to create it, which is the motivation for using corpus analyses when developing new tools and techniques. This paper describes work-in-progress towards automatically generating role shift in discourse. This effort includes consideration of the underlying representation necessary to generate a role shift automatically and a survey of current annotation approaches to ascertain whether they supply sufficient data for the representation to generate the role shift.} } @inproceedings{mulrooney:14020:sign-lang:lrec, author = {Mulrooney, Kristin and Hochgesang, Julie A. and Morris, Carla and Lee, Katie}, title = {The ``how-to'' of integrating {FACS} and {ELAN} for analysis of non-manual features in {ASL}}, pages = {123--126}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14020.html}, abstract = {The process of transcribing and annotating non-manual features presents challenges for sign language researchers. This paper describes the approach used by our research team to integrate the Facial Action Coding System (FACS) with the EUDICO Linguistic Annotator (ELAN) program to allow us to more accurately and efficiently code non-manual features. Preliminary findings are presented which demonstrate that this approach is useful for a fuller description of facial expressions.} } @inproceedings{neidle:14004:sign-lang:lrec, author = {Neidle, Carol and Liu, Jingjing and Liu, Bo and Peng, Xi and Vogler, Christian and Metaxas, Dimitris}, title = {Computer-based tracking, analysis, and visualization of linguistically significant non-manual events in {American} {Sign} {Language} ({ASL})}, pages = {127--134}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14004.html}, abstract = {Our linguistically annotated American Sign Language (ASL) corpora have formed a basis for research to automate detection by computer of essential linguistic information conveyed through facial expressions and head movements. We have tracked head position and facial deformations, and used computational learning to discern specific grammatical markings. Our ability to detect, identify, and temporally localize the occurrence of such markings in ASL videos has recently been improved by incorporation of (1) new techniques for deformable model-based 3D tracking of head position and facial expressions, which provide significantly better tracking accuracy and recover quickly from temporary loss of track due to occlusion; and (2) a computational learning approach incorporating 2-level Conditional Random Fields (CRFs), suited to the multi-scale spatio-temporal characteristics of the data, which analyses not only low-level appearance characteristics, but also the patterns that enable identification of significant gestural components, such as periodic head movements and raised or lowered eyebrows. Here we summarize our linguistically motivated computational approach and the results for detection and recognition of nonmanual grammatical markings; demonstrate our data visualizations, and discuss the relevance for linguistic research; and describe work underway to enable such visualizations to be produced over large corpora and shared publicly on the Web.} } @inproceedings{notarrigo:14015:sign-lang:lrec, author = {Notarrigo, Ingrid and Meurant, Laurence}, title = {Nonmanuals as markers of (dis)fluency}, pages = {135--142}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14015.html}, abstract = {This paper focuses on the analysis and annotation of non-manual features in the framework of a study of (dis)fluency markers in French Belgian Sign Language (LSFB). In line with Gˆtz (2013), we consider (dis)fluency as the result of the combination of many independent markers ({\`i}fluencemes{\^i}). These fluencemes may contribute either positively or negatively to the efficiency of a discourse depending on their context of appearance, their specific combination, their position and frequency. We show that the non-manual features in LSFB make distinctions within pauses and palm-up signs in a consistent way and contribute to the value of the manual marker. The selection of a limited number of relevant combinations of nonmanuals, in the context of pauses and palm-up signs, proves to simplify the annotation process and to limit the number of features to examine for each nonmanual. The gaze and the head appear to be necessary and sufficient to describe pauses and palm-up signs accurately. Though these findings are limited to this pilot study, they will pave the way to the next steps of the broader research project on (dis)fluency markers in LSFB this work is part of.} } @inproceedings{puupponen:14009:sign-lang:lrec, author = {Puupponen, Anna and Jantunen, Tommi and Takkinen, Ritva and Wainio, Tuija and Pippuri, Outi}, title = {Taking non-manuality into account in collecting and analyzing {Finnish} {Sign} {Language} video data}, pages = {143--148}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14009.html}, abstract = {This paper describes our attention to research into non-manuals when collecting a large body of video data in Finnish Sign Language (FinSL). We will first of all give an overview of the data-collecting process and of the choices that we made in order for the data to be usable in research into non-manual activity (e.g. camera arrangement, video compression, and Kinect technology). Secondly, the paper will outline our plans for the analysis of the non-manual features of this data. We discuss the technological methods we plan to use in our investigation of non-manual features (i.e. computer-vision based methods) and give examples of the type of results that this kind of approach can provide us with.} } @inproceedings{raino:14025:sign-lang:lrec, author = {Rain{\`o}, P{\"a}ivi and Huovila, Marja and Seilola, Irja}, title = {Visualizing the spatial working memory in mathematical discourse in {Finnish} {Sign} {Language}}, pages = {149--152}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14025.html}, abstract = {In this paper, we will present problems that arise when trying to render legible signed texts containing mathematical discourse in Finnish Sign Language. Calculation processes in sign language are carried out using fingers, both hands and the three-dimensional neutral space in front of the signer. Specific hand movements and especially the space in front of the body function like a working memory where fingers, hands and space are used as buoys in a regular and syntactically well-defined manner when retrieving, for example, subtotals. As these calculation processes are performed in fragments of seconds with both hands that act individually, simultaniousity and multidimensionality create problems for traditional coding and notation systems used in sign language research. Conversion to glosses or translations to spoken or written text (e.g. in Finnish or English) has proven challenging and what is most important, none of these ways gives justice to this unique concept mapping and mathematical thinking in signed language. Our proposal is an intermediary solution, a simple numeric animation while looking for a more developed, possibly a three-dimensional representation to visualise the calculation processes in signed languages.} } @inproceedings{schonstrom:14014:sign-lang:lrec, author = {Sch{\"o}nstr{\"o}m, Krister and Mesch, Johanna}, title = {Use of nonmanuals in adult {L2} signers in {Swedish} {Sign} {Language} -- Annotating the nonmanuals}, pages = {153--156}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel}, maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {31}, month = may, year = {2014}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14014.html}, abstract = {Nonmanuals serve as important grammatical markers for different syntactic constructions, e.g. marking clause types. To account for the acquisition of syntax by L2 SSL learners, therefore, we need to have the ability to annotate and analyze nonmanual signals. Despite their significance, however, these signals have yet to be the topic of research in the area of SSL as an L2. In this paper, we will provide suggestions for annotating the nonmanuals in L2 SSL learners. Data is based on a new SSL as L2 corpus from our ongoing project entitled ``L2 Corpus in Swedish Sign Language.'' In this paper, the combination of our work in grammatical analysis and in the creation of annotating standards for L2 nonmanuals, as well as preliminary results from the project, will be presented.} } @proceedings{lrec:sign-lang:12, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, title = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, url = {http://www.lrec-conf.org/proceedings/lrec2012/workshops/24.Proceedings_SignLanguage.pdf} } @inproceedings{caminero:12014:sign-lang:lrec, author = {Caminero, Javier and Rodriguez-Gancedo, Mari Carmen and Hernandez-Trapote, Alvaro and Lopez-Mencia, Beatriz}, title = {{SIGNSPEAK} Project Tools: A way to improve the communication bridge between signer and hearing communities}, pages = {1--6}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12014.html}, abstract = {The SIGNSPEAK project is aimed at developing a novel scientific approach for improving the communication between signer and hearing communities. In this way, SIGNSPEAK technology captures the video information from the signer and converts it into text. To do that, SIGNSPEAK consortium has devoted great efforts to the creation and annotation of the RWTH-Phoenix corpus. Based on it, a multimodal processing of the captured video is carried out and the resultant sign sequence is translated into natural language. Afterwards, the intended message could be communicated to hearing-able people using a text-to-speech (TTS) engine. In the reverse way, speech from hearing-able people would be transformed into text using Automatic Speech Recognition (ASR) and then the text would be processed by virtual avatars able to compose the suitable sign sequence. In SIGNSPEAK project, scientific and usability approaches have been combined to go beyond the state-of-the-art and contributing to suppress barriers between signer and hearing communities. In this work, a special stress was put in the development of a prototype and also, in setting of the grounds for future real industrial applications.} } @inproceedings{cormier:12033:sign-lang:lrec, author = {Cormier, Kearsy and Fenlon, Jordan and Johnston, Trevor and Rentelis, Ramas and Schembri, Adam and Rowley, Katherine and Adam, Robert and Woll, Bencie}, title = {From Corpus to Lexical Database to Online Dictionary: Issues in annotation of the {BSL} Corpus and the Development of {BSL} {SignBank}}, pages = {7--12}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12033.html}, abstract = {One requirement of a sign language corpus is that it should be machine-readable, but only a systematic approach to annotation that involves lemmatisation of the sign language glosses can make this possible at the present time. Such lemmatisation involves grouping morphological and phonological variants together into a single lemma, so that all related variants of a sign can be identified and analysed as a single sign. This lemmatisation process is made more straightforward by the existence of a comprehensive lexical database, as in the case for Australian Sign Language (Auslan). When annotation of data collected as part of the British Sign Language (BSL) Corpus Project began, no such lexical database for BSL existed. Therefore, a lemmatised BSL lexical database was created concurrently during annotation of the BSL Corpus data. As part of ongoing work by the Deafness Cognition {\&} Language Research Centre, this lexical database is being developed into an online BSL dictionary, BSL SignBank. This paper describes the adaptation of the Auslan lexical database into a BSL lexical database, and the current development of this lexical database into BSL SignBank.} } @inproceedings{crasborn:12031:sign-lang:lrec, author = {Crasborn, Onno and de Meijer, Anne}, title = {From corpus to lexicon: the creation of {ID-glosses} for the {Corpus} {NGT}}, pages = {13--18}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12031.html}, abstract = {When glossing of the Corpus NGT started in 2007, there was no lexicon at our disposal to base ID-glosses on. Semantic labels were used without ensuring a constant relationship between sign form and gloss. This is currently being repaired by creating a lexicon from scratch alongside with the creation of new annotations. This substantial task is still in progress, but promises to lead to several new research avenues for the future. The current paper describes some of the choices that were made in the process, and specifies some of the glossing conventions that were used.} } @inproceedings{crasborn:12030:sign-lang:lrec, author = {Crasborn, Onno and Hulsbosch, Micha and Sloetjes, Han}, title = {Linking {Corpus} {NGT} annotations to a lexical database using open source tools {ELAN} and {LEXUS}}, pages = {19--22}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12030.html}, abstract = {This paper describes how we have made a first start with expanding the functionality of the ELAN annotation tool to create a bridge to a lexical database. A first lookup facility of an annotation in a LEXUS database is created, which generates a user-configurable selection of fields from that database, to be displayed in ELAN. In addition, an extension of the (open) controlled vocabularies that can be specified for tiers allows for the creation of very large vocabularies, such as lexical items in a language. Such an `external controlled vocabulary' is an XML file that can be published on any web server and thus will be accessible to any interested party. Future development should allow for the vocabulary to be directly linked to a LEXUS database and thus also allow for access right management.} } @inproceedings{dimou:12018:sign-lang:lrec, author = {Dimou, Athanasia-Lida and Pitsikalis, Vassilis and Goulas, Theodoros and Theodorakis, Stavros and Karioris, Panagiotis and Pissaris, Michalis and Fotinea, Stavroula-Evita and Efthimiou, Eleni and Maragos, Petros}, title = {A {GSL} continuous phrase corpus: Design and acquisition}, pages = {23--26}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12018.html}, abstract = {The corpus presented in this article is composed of a limited number of Greek Sign Language (GSL) sentences and was created in order to provide additional data to the already obtained corpus during the first year of the Dicta-Sign project (Matthes et al., 2010). More specifically this corpus intended to serve as the ground upon which a significant part of the recognition process would be tested and evaluated, more precisely, the continuous sign language recognition algorithms developed in the project. \par Given the targeted nature of this corpus we present here the constraints as well as the procedure followed in order to obtain it. \par The procedure followed for the creation of this corpus, consists of its linguistic design and validation, the studio and hardware acquisition configuration, the implementation and supervision of the acquisition itself and the post-processing and annotation of the obtained data in order to release the set of usable annotated resources. The specific GSL phrase corpus forms the basis for machine learning and training to serve experimentation in the domain of continuous sign language processing and recognition.} } @inproceedings{dubot:12008:sign-lang:lrec, author = {Dubot, R{\'e}mi and Collet, Christophe}, title = {Improvements of the Distributed Architecture for Assisted Annotation of Video Corpora}, pages = {27--30}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12008.html}, abstract = {Progress on automatic annotation looks attractive for the research on sign languages. Unfortunately, such tools are not easy to deploy or share. We propose a solution to uncouple the annotation software from the automatic processing module. \par Such a solution requires many developments: design of a network stack supporting the architecture, production of a video server handling trust policies, standardization of annotation encoding. \par In this article, we detail the choices made to implement this architecture.} } @inproceedings{ebling:12010:sign-lang:lrec, author = {Ebling, Sarah and Tissi, Katja and Volk, Martin}, title = {Semi-Automatic Annotation of Semantic Relations in a {Swiss} {German} {Sign} {Language} Lexicon}, pages = {31--36}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12010.html}, abstract = {We propose an approach to semi-automatically obtaining semantic relations in Swiss German Sign Language (Deutschschweizerische Geb{\"a}rdensprache, DSGS). We use a set of keywords including the gloss to represent each sign. We apply GermaNet, a lexicographic reference database for German annotated with semantic relations. The results show that approximately 60{\%} of the semantic relations found for the German keywords associated with 9000 entries of a DSGS lexicon also apply for DSGS. We use the semantic relations to extract sub-types of the same type within the concept of double glossing (Konrad 2011). We were able to extract 53 sub-type pairs.} } @inproceedings{efthimiou:12025:sign-lang:lrec, author = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Glauert, John and Bowden, Richard and Braffort, Annelies and Collet, Christophe and Maragos, Petros and Lefebvre-Albaret, Fran{\c c}ois}, title = {Sign Language technologies and resources of the {Dicta-Sign} project}, pages = {37--44}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12025.html}, abstract = {Here we present the outcomes of Dicta-Sign FP7-ICT project. Dicta-Sign researched ways to enable communication between Deaf individuals through the development of human-computer interfaces (HCI) for Deaf users, by means of Sign Language. It has researched and developed recognition and synthesis engines for sign languages (SLs) that have brought sign recognition and generation technologies significantly closer to authentic signing. In this context, Dicta-Sign has developed several technologies demonstrated via a sign language aware Web 2.0, combining work from the fields of sign language recognition, sign language animation via avatars and sign language resources and language models development, with the goal of allowing Deaf users to make, edit, and review avatar-based sign language contributions online, similar to the way people nowadays make text-based contributions on the Web.} } @inproceedings{erlenkamp:12015:sign-lang:lrec, author = {Erlenkamp, Sonja and Eriksen, Olle}, title = {{SignWiki} -- an experiment in creating a user-based corpus}, pages = {45--48}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12015.html}, abstract = {Norwegian Sign Language (henceforth NTS for Norsk TegnSpr{\aa}k) is one of the known yet little described signed languages in Europe. Since 1825 it has been school language in Norway at schools for the deaf. As early as 1875 Norwegian Sign Language was labelled as a language (Skavlan, 1875), but as in many other western countries this attitude towards a signed language didn't survive the period of oralism and first in the late 1970s, early 1980s the idea of NTS as a natural full-fledged grammatical language evolved again. Through the past 3 decades several official documents and articles, (e.g Bergh 2004; Erlenkamp 2007; Erlenkamp et al. 2007) have operated with a number of about 4000- 5000 deaf Norwegians and an unknown number of hearing Norwegians using NTS as one of their first languages. It is estimated that about 15.000 of the 4.5 million Norwegians use this language as a first or second language. Thus, it is a rather small language community. By now, NTS has gained a relatively wide acceptance in the Norwegian Society and April 28th 2009 a proposition was passed by the Norwegian Parliament that NTS should become one of several official languages (Stortingsmelding 35 (2007/2008). \par Sign language studies and interpreting studies have been offered at several Universities and University Colleges since the mid-1990s. Moreover, in the 1990s the government established a 40 weeks free course in NTS for hearing parents of deaf children to help closing the gap between the hearing parent's signed language knowledge and skills and the practical skills of their deaf children in NTS. \par Thus, the need for documentation of the NTS in a corpus based dictionary has been evident to the field for quite a while. However, the documentation of Norwegian Sign Language has so far only been conducted by a handful of researchers and thus little research has been done on NTS. Furthermore, despite some high quality applications to raise funding for corpus work the field has not succeeded to gain enough understanding in governmental research funding institutions for the need of the small population of NTS users for a language corpus and a corpus based dictionary. Today there is only a non-corpus based dictionary project to collect signs in a kind of general sign glossary. \par As a result the field is trying out a new approach by involving the NTS community to create a larger database of signs, including their use, distribution and probably other metadata. The project aims at using a Wiki user interface, with integrated functions for use of videos where each article covers a sign with the opportunity to comment on and contribute meta-information about the sign. Like Wikipedia, the SignWiki will be open accessible, but administered by a group of experts. This form of data collection leads to some advantages in terms of being user based, but also a number of risks regarding the reliability and quality of the data. These issues will be discussed in the presentation. \par Since the project just secured funding for the next two years and still is in an early stage, there is no wiki to present yet. Instead the presentation aims at presenting the challenges and tasks in developing the wiki, like: \begin{enumerate}\item developing a user interface based on a common Wiki that allows to integrate videos and demand little experience in using the video tool\item developing a standard for each article (each article will be linked to one sign), including slots for metadata about the usage of the sign and opportunities for discussion of the sign by users\item informing and encouraging the NTS community to partake in this project\end{enumerate} \par This project is above all an attempt to involve signers in a project about their own language and gather some information of signs based on user knowledge. As a consequence, the expectations on what can be collected and the level of quality of each article have to be kept on a reasonable level. It is, however, planned to make the signs from the already existing glossary available on the wiki as well, in an attempt to obtain more information about these signs and thus hopefully to create a synergy effect between the SignWiki and dictionary project. \par Obviously a SignWiki cannot replace a scientific corpus. But if this experiment is successful it might be a good starting point for countries with no or little funding of corpus projects were the involvement of users is the key factor.} } @inproceedings{esteve:12020:sign-lang:lrec, author = {Est{\`e}ve, Isabelle}, title = {Transcribing and evaluating language skills of deaf children in a multimodal and bilingual way: the sensitive issue of the gesture/signs dynamics}, pages = {49--56}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12020.html}, abstract = {Transcribing and evaluating the narrative productions of 6 to 12 year-olds deaf children in their multimodal and bilingual dimensions confront us to the central question of gestures/signs distinction. This paper aims to discuss how the narrative skills of 30 deaf children schooled in different education settings -- oralist, bilingual and ``mixed'' -- led us to create an annotation tools in ELAN allowed to take into account the intra-modal dynamics between verbal and non-verbal material within gestural modality. We focus on two central points of our reflections. How delimit production in units into taking into account the semiotic and the structural dynamics aspects of production? How describe and categorize the gestural processes non systematized in a linguistic form to report the developmental dynamics?} } @inproceedings{fanghella:12026:sign-lang:lrec, author = {Fanghella, Julia and Geer, Leah and Henner, Jonathan and Hochgesang, Julie A. and Lillo-Martin, Diane and Mathur, Gaurav and Mirus, Gene and Pascual-Villanueva, Pedro}, title = {Linking an {ID-gloss} database of {ASL} with child language corpora}, pages = {57--62}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12026.html}, abstract = {We describe an on-going project to develop a lexical database of American Sign Language (ASL) as a tool for annotating ASL corpora collected in the United States. Labs within our team complete locally chosen fields using their notation system of choice, and pick from globally available, agreed-upon fields, which are then merged into the global database. Here, we compare glosses in the database to annotations of spontaneous child data from the BiBiBi project (Chen Pichler et al., 2010). These comparisons validate our need to develop a digital link between the database and corpus. This link will help ensure that annotators use the appropriate ID-glosses and allow needed glosses to be readily detected (Johnston, 2011b; Hanke and Storz, 2008). An ID-gloss database is essential for consistent, systematic annotation of sign language corpora, as (Johnston, 2011b) has pointed out. Next steps in expanding and strengthening our database's connection to ASL corpora include (i) looking more carefully at the source of data (e.g. who is signing, language background, age, region, etc.), (ii) taking into account signing genre (e.g. presentation, informal conversation, child-directed etc), and (iii) confronting the matter of deixis, gesture, depicting verbs and other constructions that depend on signing space.} } @inproceedings{filhol:12024:sign-lang:lrec, author = {Filhol, Michael and Braffort, Annelies}, title = {A Study on Qualification/Naming Structures in Sign Languages}, pages = {63--66}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12024.html}, abstract = {In the prospect of animating virtual signers, this article addresses the issue of representing Sign, in particular on levels not restricted to the language lexicon. In order to choose and design a suitable model, we illustrate the main steps of our corpus-based methodology for linguistic structure identification and formal description with the example of a specific structure we have named ``qualification/naming''. We also discuss its similarity and difference with other Sign properties described in the literature such as compound signs. Consequently we explain our choice for a description model that does not separate lexicon and grammar in two disjoint levels for virtual signer input.} } @inproceedings{hanke:12029:sign-lang:lrec, author = {Hanke, Thomas and K{\"o}nig, Susanne and Konrad, Reiner and Langer, Gabriele}, title = {Towards tagging of multi-sign lexemes and other multi-unit structures}, pages = {67--68}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12029.html}, abstract = {With the building of larger sign language corpora tagging, handling and analysing large amounts of data reach a new level of complexity. Efficiency and interpersonal consistency in tagging are relevant issues as well as procedures and structures to identify and tag relevant linguistic units and structures beyond and above the manual sign level. We present and discuss problems and possible solution approaches (focussing on the working environment of iLex) of how to deal with multi-unit structures and more specifically multi-sign lexemes in annotation and lexicon building.} } @inproceedings{hanke:12028:sign-lang:lrec, author = {Hanke, Thomas and Matthes, Silke and Regen, Anja and Worseck, Satu}, title = {Where Does a Sign Start and End? Segmentation of Continuous Signing}, pages = {69--74}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12028.html}, abstract = {There are two basic approaches how to segment continuous signing into individual signs:\begin{itemize}\item A sign starts where the preceding one ends (i.e. fluent signing means there are no gaps between signs)\item Transitional movements between signs do not count as part of either sign. Therefore, usually there are gaps between two signs during which the articulators move from the end of one sign to the beginning of the next.\end{itemize}Both approaches have their pros and cons. However, in the context of the DGS Corpus and the Dicta-Sign project the second approach offers advantages for the subsequent processing. Here we investigate how sensitive this approach is with respect to higher video frame rates.} } @inproceedings{jantunen:12003:sign-lang:lrec, author = {Jantunen, Tommi and Burger, Birgitta and De Weerdt, Danny and Seilola, Irja and Wainio, Tuija}, title = {Experiences collecting motion capture data on continuous signing}, pages = {75--82}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12003.html}, abstract = {This paper describes some of the experiences the authors have had collecting continuous motion capture data on Finnish Sign Language in the motion capture laboratory of the Department of Music at the University of Jyv{\"a}skyl{\"a}, Finland. Monologue and dialogue data have been recorded with an eight-camera optical motion capture system by tracking, at a frame rate of 120 Hz, the three-dimensional locations of small ball-shaped reflective markers attached to the signer's hands, arms, head, and torso. The main question from the point of view of data recording concerns marker placement, while the main themes discussed concerning data processing include gap-filling (i.e. the process of interpolating the information of missing frames on the basis of surrounding frames) and the importing of data into ELAN for subsequent segmentation (e.g. into signs and sentences). The paper will also demonstrate how the authors have analyzed the continuous motion capture data from the kinematic perspective.} } @inproceedings{karpov:12012:sign-lang:lrec, author = {Karpov, Alexey and {\v Z}elezn{\'y}, Milo{\v s}}, title = {Towards {Russian} {Sign} {Language} Synthesizer: Lexical Level}, pages = {83--86}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12012.html}, abstract = {In this paper, we present a survey of existing Russian sign language electronic and printed resources and dictionaries. The problem of differences in dialects of Russian sign language used in various local communities of Russia and some other CIS countries is discussed in the paper. Also the first version of a computer system for synthesis of elements of Russian sign language (signed Russian and fingerspelling) is presented in the given paper. It is a universal multi-modal synthesizer both for Russian spoken language and signed Russian that is based on a model of animated 3D signing avatar. The proposed system inputs data in the text form and converts them into the audio-visual modality, synchronizing visual manual gestures and articulation with audio speech signal. Generated audio-visual signed Russian speech and spoken language is a fusion of dynamic gestures shown by the avatar{\'i}s both hands, lip movements articulating words and auditory speech, so the multimodal output is available both for the deaf and hearing-able people.} } @inproceedings{konrad:12023:sign-lang:lrec, author = {Konrad, Reiner and Hanke, Thomas and K{\"o}nig, Susanne and Langer, Gabriele and Matthes, Silke and Nishio, Rie and Regen, Anja}, title = {From form to function. A database approach to handle lexicon building and spotting token forms in sign languages}, pages = {87--94}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12023.html}, abstract = {Using a database with type entries that are linked to token tags in transcripts has the advantage that consistency in lemmatising is not depending on ID-glosses. In iLex types are organised in different levels. The type hierarchy allows for analysing form, iconic value, and conventionalised meanings of a sign (sub-types). Tokens can be linked either to types or sub-types. \par We expanded this structure for modelling sign inflection and modification as well as phonological variation. Differences between token and type form are grouped by features, called qualifiers, and specified by feature values (vocabularies). Built-in qualifiers allow for spotting the form difference when lemmatising. This facilitates lemma revision and helps to get a clear picture of how inflection, modification, or phonological variation is distributed among lexical signs. This is also a strong indicator for further POS tagging. In the long term this approach will extend the lexical database from citation-form closer to full-form. \par The paper will explain the type hierarchy and introduce the qualifiers used up-to-date. Further on the handling and how the data are displayed will be illustrated. As we report work in progress in the context of the DGS corpus project, the modelling is far from complete.} } @inproceedings{kristoffersen:12032:sign-lang:lrec, author = {Kristoffersen, Jette and Troelsg{\aa}rd, Thomas}, title = {Integrating corpora and dictionaries: problems and perspectives, with particular respect to the treatment of sign language}, pages = {95--100}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12032.html}, abstract = {In this paper, we will discuss different possibilities for integration of corpus data with dictionary data, mainly seen from a lexicographic point of view and in a sign language context. For about 25 years a text corpus has been considered a useful, if not necessary tool for editing dictionaries of written and spoken languages. Corpora are equally useful to sign language lexicographers, but sign language corpora have not become accessible until recent years. Nowadays corpora exist, or are being developed, for several sign languages, and we have the possibility of editing new, truly corpus-based sign language dictionaries, and of developing interfaces that integrate corpus and dictionary data. After a brief look at three existing integrated interfaces, one for German, one for Danish, and one for Danish Sign Language, we point out some of the problems that should be considered when making an integrated interface, and, finally, we briefly outline the future perspectives of integrated sign language corpus-dictionary interfaces.} } @inproceedings{langer:12017:sign-lang:lrec, author = {Langer, Gabriele}, title = {A colorful first glance at data on regional variation extracted from the {DGS-Corpus}: With a focus on procedures}, pages = {101--108}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12017.html}, abstract = {In this work in progress procedures for analyzing and displaying distributional patterns of sign variants have been developed and tested on data for color signs elicited by the DGS Corpus Project. The data for this preliminary study were elicited as isolated signs and have been made accessible through spot annotations in iLex. The annotations had not been lemma revised but nevertheless revealed some interesting insights. Several color signs exhibited a high degree of variation. The distributional maps showed that a number of signs were mainly used in certain regions and thus provided evidence on dialectal differences within DGS. The relevant information necessary to generate distributional maps have been directly extracted via SQL-statements from the corpus and fed into R. The approach is data driven. The distributional maps show either the distribution of one sign form (variant) or of several different variants in relation to each other. Analyses of regional distribution as displayed by the distributional maps may support the annotation and lemma revision process and are a valuable basis for a lexicographical description of signs and their use as needed for compiling dictionary entries. A refined procedure to take multiple regional influences on informants into account for analysis is proposed.} } @inproceedings{lu:12005:sign-lang:lrec, author = {Lu, Pengfei and Huenerfauth, Matt}, title = {{CUNY} {American} {Sign} {Language} Motion-Capture Corpus: First Release}, pages = {109--116}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12005.html}, abstract = {We are in the middle of a 5-year study to collect, annotate, and analyze an ASL motion-capture corpus of multi-sentential discourse. Now we are ready to release to the research community the first sub-portion of our corpus that has been checked for quality. This paper describes the recording and annotation procedure of our released corpus to enable researchers to determine if it would benefit their work. A focus of the collection process was the identification and use of prompting strategies for eliciting single-signer multi-sentential ASL discourse that maximizes the use of pronominal spatial reference yet minimizes the use of classifier predicates. The annotation of the corpus includes details about the establishment and use of pronominal spatial reference points in space. Using this data, we are seeking computational models of the referential use of signing space and of spatially inflected verb forms for use in American Sign Language (ASL) animations, which have accessibility applications for deaf users.} } @inproceedings{matthes:12016:sign-lang:lrec, author = {Matthes, Silke and Hanke, Thomas and Regen, Anja and Storz, Jakob and Worseck, Satu and Efthimiou, Eleni and Dimou, Athanasia-Lida and Braffort, Annelies and Glauert, John and Safar, Eva}, title = {{Dicta-Sign} -- Building a Multilingual Sign Language Corpus}, pages = {117--122}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12016.html}, abstract = {This paper presents the multilingual corpus of four European sign languages compiled in the framework of the Dicta-Sign project. Dicta-Sign researched ways to enable communication between Deaf individuals through the development of human-computer interfaces (HCI) for Deaf users, by means of sign language. Sign language resources were compiled to inform progress in the other research areas within the project, especially video recognition of signs, sign-to-sign translation, linguistic modelling, and sign generation. The aim for the corpus data collection was to achieve as high a level of naturalness as possible with semi-spontaneous utterances under lab conditions. At the same time the elicited data were supposed to be semantically close enough to be comparable both across individual informants and for all four sign languages. The sign language data were annotated using iLex and are now made available via a web portal that allows for different access options to the data.} } @inproceedings{mesch:12002:sign-lang:lrec, author = {Mesch, Johanna and Wallin, Lars}, title = {From meaning to signs and back: Lexicography and the {Swedish} {Sign} {Language} Corpus}, pages = {123--126}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12002.html}, abstract = {In this paper, we will present the advantages of having a reference dictionary, and how having a corpus makes dictionary making easier and more effective. It also gives a new perspective on sign entries in the dictionary, for example, if a sign uses one or two hands, or which meaning {\`i}genuine signs{\^i} have, and it helps find a model for categorization of polysynthetic signs that is not found in the dictionary. Categorizing glosses in the corpus work has compelled us to revisit the dictionary to add signs from the corpus that are not already in the dictionary and to improve sign entries already in the dictionary based on insights that have been gained while working on the corpus.} } @inproceedings{mesch:12001:sign-lang:lrec, author = {Mesch, Johanna and Wallin, Lars and Bj{\"o}rkstrand, Thomas}, title = {Sign Language Resources in {Sweden}: Dictionary and Corpus}, pages = {127--130}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12001.html}, abstract = {Sign language resources are necessary tools for adequately serving the needs of learners, teachers and researchers of signed languages. Among these resources, the Swedish Sign Language Dictionary was begun in 2008 and has been in development ever since. Today, it has approximately 8,000 sign entries. The Swedish Sign Language Corpus is also an important resource, but it is of a very different kind than the dictionary. Compiled during the years 2009--2011, the corpus consists of video recorded conversations among 42 informants aged between 20 and 82, from three separate regions in Sweden. With 14 {\%} of the corpus having been annotated with glosses for signs, it comprises total of approximately 3,600 different signs occurring about 25,500 times (tokens) in the 42 annotated sign language discourses/video files. As these two resources sprang from different starting points, they are independent from each other; however, in the late phases of building the corpus the importance of combining work from the two became evident. This presentation will show the development of these two resources and the advantages of combining them.} } @inproceedings{moreau:12021:sign-lang:lrec, author = {Moreau, C{\'e}dric}, title = {A conceptual approach in sign language classification for concepts network}, pages = {131--136}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12021.html}, abstract = {Most websites presuppose a conceptual equivalence between a written word and a sign. In such tools, signs which don't have strict written equivalent lexicons cannot be found. The collaborative website OCELLES project LSF/French tries to give the opportunity to obtain several signs for a unique concept, with the possibility of uploading a sign without being constrained by written language. Although word checking in a written text is quite easy, it is not the case for sign checking in a video. Today studies are carried out in the field of gesture recognition, but all the sign language linguistic parameters cannot be considered as such. Indeed, they have to be used simultaneously during communication interactions. Our approach based upon the semiological Cuxac model (Cuxac, 2000) and Thom morphogenesis theory (Thom, 1973), could help to find a sign in a sign dictionary without using any written language.} } @inproceedings{neidle:12027:sign-lang:lrec, author = {Neidle, Carol and Vogler, Christian}, title = {A New Web Interface to Facilitate Access to Corpora: Development of the {ASLLRP} Data Access Interface}, pages = {137--142}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12027.html}, abstract = {A significant obstacle to broad utilization of corpora is the difficulty in gaining access to the specific subsets of data and annotations that may be relevant for particular types of research. With that in mind, we have developed a web-based Data Access Interface (DAI), to provide access to the expanding datasets of the American Sign Language Linguistic Research Project (ASLLRP). The DAI facilitates browsing the corpora, viewing videos and annotations, searching for phenomena of interest, and downloading selected materials from the website. The web interface, compared to providing videos and annotation files off-line, also greatly increases access by people that have no prior experience in working with linguistic annotation tools, and it opens the door to integrating the data with third-party applications on the desktop and in the mobile space. In this paper we give an overview of the available videos, annotations, and search functionality of the DAI, as well as plans for future enhancements. We also summarize best practices and key lessons learned that are crucial to the success of similar projects.} } @inproceedings{neidle:12011:sign-lang:lrec, author = {Neidle, Carol and Thangali, Ashwin and Sclaroff, Stan}, title = {Challenges in Development of the {American} {Sign} {Language} Lexicon Video Dataset ({ASLLVD}) Corpus}, pages = {143--150}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12011.html}, abstract = {The American Sign Language Lexicon Video Dataset (ASLLVD) consists of videos of >3,300 ASL signs in citation form, each produced by 1-6 native ASL signers, for a total of almost 9,800 tokens. This dataset, including multiple synchronized videos showing the signing from different angles, will be shared publicly once the linguistic annotations and verifications are complete. Linguistic annotations include gloss labels, sign start and end time codes, start and end handshape labels for both hands, morphological and articulatory classifications of sign type. For compound signs, the dataset includes annotations for each morpheme. To facilitate computer vision-based sign language recognition, the dataset also includes numeric ID labels for sign variants, video sequences in uncompressed-raw format, camera calibration sequences, and software for skin region extraction. We discuss here some of the challenges involved in the linguistic annotations and categorizations. We also report an example computer vision application that leverages the ASLLVD: the formulation employs a HandShapes Bayesian Network (HSBN), which models the transition probabilities between start and end handshapes in monomorphemic lexical signs. Further details and statistics for the ASLLVD dataset, as well as information about annotation conventions, are available from http://www.bu.edu/asllrp/lexicon.} } @inproceedings{othman:12019:sign-lang:lrec, author = {Othman, Achraf and Jemni, Mohamed}, title = {{English-ASL} Gloss Parallel Corpus 2012: {ASLG-PC12}}, pages = {151--154}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12019.html}, abstract = {A serious problem facing the Community for researchers in the field of sign language is the absence of a large parallel corpus for signs language. The ASLG-PC12 project proposes a rule-based approach for building big parallel corpus between English written texts and American Sign Language Gloss. We present a novel algorithm which transforms an English part-of-speech sentence to ASL gloss. This project was started in the beginning of 2011, a part of the project WebSign, and it offers today a corpus containing more than one hundred million pairs of sentences between English and ASL gloss. It is available online for free in order to develop and design new algorithms and theories for American Sign Language processing, for example statistical machine translation and any related fields. In this paper, we present tasks for generating ASL sentences from the corpus Gutenberg Project that contains only English written texts.} } @inproceedings{sze:12022:sign-lang:lrec, author = {Sze, Felix and Woodward, James and Tang, Gladys and Lee, Jafi and Cheng, Ka-Yiu and Mak, Joe}, title = {Sign Language Documentation in the {Asia-Pacific} Region: A Deaf-centred approach}, pages = {155--158}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12022.html}, abstract = {In this paper, we would like to share our experience in training up Deaf individuals from the Asian-Pacific countries to compile sign language dictionaries and conduct sign language research through the `Asia-Pacific Sign Linguistics Research and Training Program' at the Chinese University of Hong Kong. The program, fully funded by the Nippon Foundation, is a multi-country, multi-phase project which aims at nurturing Deaf people to become sign language researchers through a series of credit-bearing training programs at the diploma and higher diploma levels. The training covers three major areas: Sign Linguistics, Sign Language Teaching and English Literacy. One important part of the training involves the production of sample dictionaries of the Deaf trainees' own sign languages. To confirm the dictionary entries, the Deaf trainees conduct surveys in the Deaf communities in their home countries from time to time and as a result a substantial amount of lexical variants have been collected. An online database, called the Asian SignBank, is now being developed to house these lexical data and facilitate further research. Apart from basic search functions, the SignBank also incorporates detailed phonetic features of individual signs and a materials-generating function which allows quicker production of dictionaries in the future.} } @inproceedings{vintar:12007:sign-lang:lrec, author = {Vintar, {\v S}pela and Jerko, Bo{\v s}tjan and Kulovec, Marjetka}, title = {Compiling the {Slovene} {Sign} {Language} Corpus}, pages = {159--162}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12007.html}, abstract = {We report on the project of compiling the first corpus of the Slovene Sign Language. The paper describes the procedures of data collection, the decisions regarding informant selection and plans for transcription and annotation. We outline the particularities of the Slovene situation, especially the high variability of the language, issues concerning language competence and the attitutes of the deaf community towards such data collection. At the time of writing, the data collection stage is nearly finished with over 70 recorded persons, and trancriptions with iLex are underway. The aim of the project is to use the corpus for explorations into the grammatical properties of SSL.} } @inproceedings{wolfe:12006:sign-lang:lrec, author = {Wolfe, Rosalee and McDonald, John C. and Toro, Jorge and Schnepp, Jerry}, title = {A Proposal for Making Corpora More Accessible for Synthesis: A Case Study Involving Pointing and Agreement Verbs}, pages = {163--166}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12006.html}, abstract = {Sign language corpora serve many purposes, including linguistic analysis, curation of endangered languages, and evaluation of linguistic theories. They also have the potential to serve as an invaluable resource for improving sign language synthesis. Making corpora more accessible for synthesis requires geometric as well as linguistic data. We explore alternate approaches and analyze the tradeoffs for the case of synthesizing indexing and agreement verbs. We conclude with a series of questions exploring the feasibility of utilizing corpora for synthesis.} } @proceedings{lrec:sign-lang:10, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, title = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, url = {http://www.lrec-conf.org/proceedings/lrec2010/workshops/W13.pdf} } @inproceedings{johnston:10002:sign-lang:lrec, author = {Johnston, Trevor}, title = {Adding value to, and extracting of value from, a signed language corpus through secondary processing: implications for annotation schemas and corpus creation}, pages = {137--142}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10002.html}, abstract = {A basic signed language (SL) corpus is created through primary processing of video recordings using multi{\_}media annotation software. Primary processing entails the tokenization and identification of SL units. For the purposes of linguistic research a corpus also needs secondary processing. Secondary processing entails appending tags for specific linguistic features to primary annotations. I draw on the experience from the Auslan corpus project to describe how primary and secondary processing can be used in corpus-based SL research. In particular, I show how the tier structure of ELAN can be used to tag SL units in a variety of ways, and how this information can be used to glean new information from the corpus which can then be added as new annotations to the corpus. Value-adding by principled and systematic primary and secondary processing of digital recordings is thus not only essential for corpus creation ('machine-readability'), it also enables further enriching of the corpus so that even more value can be extracted. I conclude by discussing the implications for annotation software and standardized annotation schemas used in the creation of SL corpora.} } @inproceedings{machadooliveira:10057:sign-lang:lrec, author = {Machado Oliveira, Carlos R.}, title = {Adapting an Efficient Entry System for Sign Languages}, pages = {147--149}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10057.html}, abstract = {Building sign language written corpora may, combined with video corpora linguistics, provide richer sign language research frameworks. Tools that allow direct sign language writing could increase sign language corpora availability significantly. Here, adaptation of a free efficient computer entry system to allow sign writingis presented.} } @inproceedings{schembri:10050:sign-lang:lrec, author = {Schembri, Adam and Crasborn, Onno}, title = {Issues in creating annotation standards for sign language description}, pages = {212--216}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10050.html}, abstract = {In this paper, we discuss the need for a standardised system of annotation for sign language corpora. Although several tools exist for the annotation of video data (such as ELAN or iLex), and some existing projects have annotation guidelines (e.g., Crasborn et al., 2007; Johnston, 2010), a widely adopted standard is currently unavailable. First, we discuss the purpose of a set of unified annotation standards for sign languages: such standards would provide a shared set of conventions for the easy exchange of data across different sign language corpus projects and may increase consistency within corpora. Next, we discuss the properties that would define a good set of shared annotation conventions (Beckman et al., 2009). We examine some of the proposed annotation standards for spoken language description, such as the ToBI conventions for prosody and the Leipzig Glossing Rules for morpho-syntax. Lastly, we discuss the relationship between theory and description. Dryer (2006) pointed out that linguists often contrast 'theoretical linguistics' with 'descriptive' work. But if one accepts the argument that there is indeed no 'atheoretical description', then sign language linguists need to agree on a shared theory for basic sign language description, and how this translates into annotation practices.} } @inproceedings{almohimeed:10025:sign-lang:lrec, author = {Almohimeed, Abdulaziz and Wald, Mike and Damper, Robert}, title = {An {Arabic} {Sign} {Language} Corpus for Instructional Language in School}, pages = {7--10}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10025.html}, abstract = {Machine translation (MT) technology has made significant progress over the last decade and now offers the potential for Arabic sign language (ArSL) signers to access text published in Arabic. The dominant model of MT is now corpus based. In this model, the accuracy of translation correlates directly with size and coverage of the corpus. The corpus is a collection of translation examples constructed from existing documents such as books and newspapers; however, no written system for sign language (SL) comparable to that used for natural language has yet been developed. Hence, no SL documents exist, complicating the procedure for constructing an SL corpus. In countries such as Ireland and Germany, a number of corpora have already been developed from scratch and used for MT. There is no ArSL corpus for MT, requiring the creation of a new ArSL corpus for language instruction. The goal of building this corpus is to develop an automatic translation system from Arabic text to ArSL. \par This paper presents the ArSL corpus for instructional language constructed for use in schools, and the methodology used to create it. The corpus was collected at the College of Computer and Information Sciences at Imam Muhammad bin Saud University in Riyadh, Saudi Arabia. A group of interpreters and native signers with backgrounds in education were involved in this work. \par The corpus was constructed by collecting instructional sentences used daily in schools for the deaf. The syntax and morphology of each sentence were then manually analysed. Each sentence was individually translated, recorded on video, and stored in MPEG format. The corpus contains video data from three native signers. The videos were then annotated using an ELAN annotation tool. The annotated video data contain isolated signs accompanied by detailed information, such as manual and non-manual features. The last procedure in constructing the corpus was to create a bilingual dictionary from the annotated videos. \par The corpus comprises two main parts. The first part is the annotated video data, comprising isolated signs with detailed information, accompanied by manual and non-manual features. It also contains the Arabic translation script, including syntax and morphology details. The second part is the bilingual dictionary, delivered with the annotated videos.} } @inproceedings{balvet:10046:sign-lang:lrec, author = {Balvet, Antonio}, title = {Issues underlying a common Sign Language Corpora annotation scheme}, pages = {15--18}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10046.html}, abstract = {Corpus-based Sign Language linguistics has emerged as a new linguistic domain, and as a consequence large-scale and controlled video data repositories are under construction for different Sign Languages. \par Nevertheless, as pointed by (Johnston, 2008) no unified annotation scheme is yet available, which compromises any chance of comparing or reusing corpora across research teams. Another related issue is the comparability of descriptions and formalizations between SL linguistics and mainstream linguistics. In this paper, we address the issue of the definition of a common annotation scheme for Sign Language corpora annotation, distribution, exchange and comparison. In section 2. we discuss the challenge of building inter-operable corpora for corpus-based linguistics. We also examine existing annotation schemes or strategies proposed for SL linguistics. \par In section 3. we propose a small set of annotation tiers, based on Frame-Semantics, as a common annotation scheme. We also propose to add text-level as well as utterance-level metadata to this common annotation scheme, in order to broaden the range of future uses of SL corpora.} } @inproceedings{conte:10024:sign-lang:lrec, author = {Conte, Genny and Santoro, Mirko and Geraci, Carlo and Cardinaletti, Anna}, title = {Why are you raising your eyebrows?}, pages = {53--56}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10024.html}, abstract = {It is widely known that sign languages make an extensive use of non-manual markers (NMM) to transmit linguistic information. Some NMMs are specific to particular constructions (in several Sign Languages, furrowed eyebrows is mostly used to mark wh-questions, while headshake is used to mark negation), others may occur in several unrelated constructions (see eyebrow raising in American sign language). This study presents preliminary results of a quantitative investigation of the distribution of raised eyebrows (re-NMM) in Italian Sign Language (LIS). Re-NMM frequently occurs in spontaneous signing and is used to mark a variety of constructions; therefore re-NMM qualifies as a good candidate for a VARBRUL analysis. In particular, re-NMM may mark 8 different constructions in LIS: yes/no-questions, topics, if-clauses, correlative clauses, focus, contrastive focus, subordinate clauses, and the signer's attitude. Data come from a corpus of LIS and have been analyzed with the ELAN software. Results show an even distribution across the sample for most of the uses of re-NMM. Only two functions turned out to be significantly different: the use of re-NMM as a focus marker and the use of re-NMM as an attitude marker, which are sensitive to age.} } @inproceedings{efthimiou:10005:sign-lang:lrec, author = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Dimou, Athanasia-Lida and Kalimeris, Constandinos}, title = {Towards decoding Classifier function in {GSL}}, pages = {76--79}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10005.html}, abstract = {Here we will present work based on a corpus specially designed and elicited in order to provide data for the study of Classifier function in Greek Sign Language (GSL). \par Data elicitation was based on presentation to informants of a series of stimuli which lead to utterances entailing the set of Classifier functions met in the language. \par The whole set of video recorded data were annotated in order to provide an appropriate corpus for the investigation of Classifier instantiations. Annotation work was complemented by the use of a search tool external to the ELAN environment, which was developed in order to handle the whole of annotated material. This search tool allows to create a data base of annotated video clips, by exploiting the set of classification features used to annotate the video recorded data. Among the attribute-value pairs forming the complete set of annotation features used, the following tiers of annotation were adopted: a) "Discourse Unit", indicating the sentence or utterance in which a classifier is met, b) "CP{\_}{\_}{\_}{\_}" for marking the maximal classifier predicate, c) "CP{\_}GLOSS" to describe the semantic content of classifiers, and d) "HS" with font symbols as values for specifying the handshape or handshapes involved in signing. These tiers provide the necessary information to group pieces of data as to the different classifiers and classifier functions met in GSL, i.e. [Discourse Unit: various types of tables], [CP{\_}MAX: round tables of different sizes], [CP{\_}GLOSS: ROUND, FLAT, SIZE], [HS: D, L, B...]. \par Theoretical analysis of the so created linguistic data supports formulation of a proposal for Classifier behaviour which differentiates among three distinguished major grammar functions. The key property that allows for a principled account of Classifier behaviour is that Classifiers are semantic markers which create semantic classes of objects recognised to share a set of common semantic features. \par In this line, we will argue that Classifiers are morphemes articulated according to SL phonology primes. According to our proposal GSL utilises Classifier morphemes in three distinct ways:\begin{enumerate}\item To create new lexicon items: Classifier affixation adds specific semantic properties to an entity, making it part of the semantic class this specific Classifier identifies.\item To add qualitative/quantitative values: Classifiers function as modifiers adding qualitative/quantitative values to syntactic heads or maximal phrases.\item To serve co-indexing: In sign utterances, Classifiers may be used as pronominal elements, where co-indexing obligatorily involves an expanded set of agreement features which, apart from the standard features "Number" and "Gender", also includes the feature "Semantic Class".\end{enumerate}} } @inproceedings{ivanova:10009:sign-lang:lrec, author = {Ivanova, Nedelina}, title = {The {Icelandic} sign language dictionary project: some theoretical issues}, pages = {125--128}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10009.html}, abstract = {There are approximately 300 deaf users of Icelandic Sign Language ({\'I}slenskt t{\'a}knm{\'a}l, ITM). The first dictionary of ITM was published in 1976 and was last edited in 1988. The ITM dictionary is a wordlist consisting of illustrations of the signs, sometimes specially invented for the list's purpose, presenting an Icelandic word or an inflected form of a common Icelandic verb and loans from Swedish and Danish Sign Language because it was considered that the total number of signs was insufficient. In 2004 The Association of Parents and Benefit Society of Hard of Hearing children subsidized a compilation of signs which was published on the Internet under the name The sign bank. The novelty is that signs are shown by `demo video clips'. Actual lexicographical work has not been done in this field in Iceland. These circumstances call for a compilation of an electronic dictionary of ITM based on linguistic principles and lexicographical methods. \par The facts that dictionary compilation for SL is in general time-consuming, expensive and the limited number of potential users similarly to ITM make the work on a dictionary of ITM very difficult. The dictionary project for ITM has been more or less at a theoretical stage during the last two years, starting in 2008 with a M.A. thesis on lexicographical description for an electronic dictionary of ITM on the basis of linguistic principles and in 2009 with a description of a lexical bilingual database for the dictionary compilation. At the same time in 2009 a list of 6441 signs was compiled by Deaf and hearing researchers at the Communication Centre for The Deaf and Hard of Hearing. Today in 2010 the project is on hold due to financial reasons. \par However, the electronic dictionary project of ITM is the first incisive research of ITM lexicon. The purpose with ITM dictionary with its 4000 entries, when published, is to give answers concerning sign's base form, meaning and appropriate usage. \par This paper reports on the lexicographical description for construction of a dictionary for ITM. The author reviews briefly some theoretical issues regarding the dictionary's project: the languages in the dictionary and its potential users, sign's collection, evaluation and selection, the lemmatizing process, the dictionary entry, access structures, the dictionary article and two practical problems. The languages in the dictionary are Icelandic and ITM, with Icelandic as L1 and ITM as L2. Potential users of the dictionary include members of the general public interested in ITM; parents of Deaf children and their hearing friends, interpreters and hearing people teaching ITM, students in Sign Language studies, people who attend SL courses as well as the Deaf people themselves. Signs, thought to be every day vocabulary and used by most of the Deaf people, would to be found in the dictionary. The dictionary entry is a sign in its base form shown by `demo video clip' and an Icelandic gloss. The lemma selection for lexical items with identical base form is influenced by mouth movements and mouth gestures as a lexicalized part of the lemma on the semantic level. The dictionary's access structure requires every sign's phonological description. With the potential users in mind, many access possibilities make the search for a sign easy and quick. It is possible to search in the dictionary after four criteria based on phonological structure of signs, after picture themes with illustrations and an Icelandic word. In the dictionary article phonological information is given by pictures which show sign's handshape and location; sign's meaning is given by Icelandic equivalent(s) or explanation(s); sign's modification for subject-object verb agreement is shown by example and sign's modification for plural is shown by link to the correspondent part in the explanatory grammar chapter in the dictionary. Information on the use of the entry is given by example which consists of `demo video clip', sentence's gloss and Icelandic translation. Practical problems concern e.g. the presentation of classifier predicates in the dictionary article and the low reliability of hearing researcher moderating discussion sessions with Deaf informants. \par In conclusion, the paper highlights the dictionary's importance for (1) documentation and basic research of ITM and (2) getting legal recognition of the language.} } @inproceedings{jantunen:10033:sign-lang:lrec, author = {Jantunen, Tommi}, title = {A comparison of two linguistic sign identification methods}, pages = {129--132}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10033.html}, abstract = {This paper employs two linguistic sign identification methods -- a manual one focusing on the dominant hand and a nonmanual one focusing on the mouth -- and compares the kinds of sequences they classify as signs from a video containing continuous signing. The study is motivated by two projects, of which one investigates the ontological nature of the sign and the other aims to develop an automatic sign recognition tool. In the study, both methods were able to associate all the free semantic-functional elements in the data with signs. However, in the nonmanual method the overall number of identified signs was lower because the stretching of the mouth movement of the semantic element over the following pointing meant that the combinations of semantic elements and pointings were counted as single signs. Moreover, signs identified by the nonmanual method were longer than those identified by the manual method. The results from the nonmanual method agree with the claim that phrase internal sequences of semantic elements and pointings are lexical head plus clitic combinations. Consequently, it is suggested that pointings in such contexts do not need to be independently detected by the automatic sign recognition tool.} } @inproceedings{ormel:10036:sign-lang:lrec, author = {Ormel, Ellen and Crasborn, Onno and van der Kooij, Els and van Dijken, Lianne and Nauta, Ellen Yassine and Forster, Jens and Stein, Daniel}, title = {Glossing a multi-purpose sign language corpus}, pages = {186--191}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10036.html}, abstract = {This paper describes the strategies that have been developed for creating consistent gloss annotations in the latest update to the Corpus NGT. Although the project aims to embrace the plea for ID-glosses in Johnston (2008), there is no reference lexicon that could be used in the creation of the annotations. An idiosyncratic strategy was developed that involved the creation of a temporary `glossing lexicon', which includes conventions for distinguishing regional and other variants, true and apparent homonymy, and other difficulties that are specifically related to the glossing of two-handed simultaneous constructions on different tiers.} } @inproceedings{thorvaldsdottir:10016:sign-lang:lrec, author = {Thorvaldsdottir, Gudny Bjork}, title = {You Get Out What You Put In: The Beginnings of Phonetic and Phonological Coding in the Signs of {Ireland} Digital Corpus}, pages = {235--238}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10016.html}, abstract = {This poster discusses a range of issues with respect to expanding the annotation of the Signs of Ireland (SOI) corpus to incorporate phonetic and phonological coding. This forms part of ongoing PHD research work that explores the phonology-morphology interface in Irish Sign Language (ISL). \par The SOI corpus consists of over 40 narratives that have already been highly annotated: it contains glossed lexical signs, classifier constructions and non-manual features. Classifier handshapes have also been annotated. It is my intention to identify the phonemes and the allophones of ISL using the corpus and it is thus neccessary to incorporate a detailed annotation at the phonetic level. \par In order to achieve this, a list of phonetic features for ISL must be identified. To date no research has been done in this area apart from basic work describing handshapes in ISL. Thus far, there is no agreement on the phonetic alphabet inventory for ISL: {\'O}'Baoill and Matthews (2000) identified 66 handshapes while Matthews (2005) identified 78. The issue of allophonic variation has not yet been tackled for this language. \par For annotation purposes, challenges arise in terms of how handshapes are recorded: for example, of the 66 handshapes identified in {\'O}'Baoill and Matthews (2000), 28 are established as occurring as classifier handshapes also. These are annotated following ECHO project annotation norms (Nonhebel et al. 2004) where possible, with additional handshapes drawn from a list of 48 classifier handshapes described for BSL in Brennan (1992) using names like CL-B, CL-ISL-K etc. within the framework of the SOI corpus. \par The other parameters that have traditionally been used to describe signs (i.e. location, movement and orientation) have not been researched in ISL at phonological or morphological level. All that currently exists is a vaguely phonetic level description of parameters respect to research on American Sign Languge (ASL) (See O'Baoill and Matthews 2000; Matthews 2005). \par This poster outlines how, by drawing on Crasborn's (2001) and van der Kooij's (2002) work on Sign Language of the Netherlands (SLN), a list of phonetic features have been established for ISL and the changes to the original list of features that were required in order to accommodate ISL. \par I also outline the factors influencing decisions regarding the coding and naming of handshapes at phonetic level. These include the question of whether already established naming conventions be maintained. For example, moving away from established protocols will result in inconsistencies within the annotations in the corpus. However, for the purposes of phonetic research a more elaborate coding might be necessary. Another challenge involves establishing what types of tiers are needed to accommodate the proposed research as well as future research at the phonetic and phonological level.} } @inproceedings{wheatley:10040:sign-lang:lrec, author = {Wheatley, Mark and Pabsch, Annika}, title = {Sign Language in {Europe}}, pages = {251--254}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10040.html}, abstract = {Sign languages across the globe are fully-fledged languages that differ between Deaf communities throughout Europe and the world. A recent survey by the European Union of the Deaf gathered that there are about 650,000 sign language users in the EU for whom using a sign language is the only way to communicate and have equal access. It is therefore crucial to legally recognise national sign languages. Being treated equally without prejudice also with regards to language is a basic Human Right as postulated in the UN Declaration of Human Rights. Other rights, such as the right to education and a fair trial can only be guaranteed if sign languages are recognised as distinct languages in order to provide sign language interpreters and education in sign language. At EU level, a number of documents and Resolutions have been adopted but so far only three European countries have recognised sign language at constitutional level: Austria, Finland and Portugal. Other countries, such as Hungary and Spain have taken other legal measures to protect their sign languages. Although Europe's sign languages enjoy some recognition, sign language users across Europe are still lacking legal protection at the same level as other minorities.} } @inproceedings{bertoldi:10054:sign-lang:lrec, author = {Bertoldi, Nicola and Tiotto, Gabriele and Prinetto, Paolo and Piccolo, Elio and Nunnari, Fabrizio and Lombardo, Vincenzo and Mazzei, Alessandro and Damiano, Rossana and Lesmo, Leonardo and Del Principe, Andrea}, title = {On the creation and the annotation of a large-scale {Italian-LIS} parallel corpus}, pages = {19--22}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10054.html}, abstract = {This paper presents the current development of the first large parallel corpus between Italian and Italian Sign Language (Lingua Italiana dei Segni, LIS). This initiative has been taken within the ATLAS project (Automatic Translation into Sign Languages), that aims at realizing a virtual interpreter, which automatically translates an Italian text into LIS. \par The Italian-LIS virtual interpreter is implemented by means of two modules interfaced by the ATLAS Extended Written LIS (AEWLIS), which is a translation-oriented representation of LIS: The first module translates the source Italian text into AEWLIS; the second module transforms the AEWLIS content into a coherent LIS sequence, smoothly animated by a virtual character. \par As no significant amount of electronic data are available for Italian and LIS, we have started building a parallel corpus from scratch in order to train and tune the Italian-AEWLIS translation system, and to compare the resulting virtual animations with human-performed LIS interpretations. The corpus, which will be freely available, actually presents a tri-lingual structure, with the Italian text, the AEWLIS sequence, and the signed LIS video.} } @inproceedings{geraci:10023:sign-lang:lrec, author = {Geraci, Carlo and Bayley, Robert and Branchini, Chiara and Cardinaletti, Anna and Cecchetto, Carlo and Donati, Caterina and Giudice, Serena and Mereghetti, Emiliano and Poletti, Fabio and Santoro, Mirko and Zucchi, Sandro}, title = {Building a corpus for {Italian} {Sign} {Language}. Methodological issues and some preliminary results}, pages = {98--101}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10023.html}, abstract = {The aim of this paper is to discuss some methodological issues that emerged during the creation of a corpus of data for Italian Sign Language, LIS. Data were collected from 10 cities spread across the country. 18 signers from each city have been recruited. They are native speakers of LIS or later-exposed to LIS and are divided into 3 age groups (19-38, 39-58, 59-78) of 6 signers each (3 males and 3 females). The methodology of data collection and transcription is similar to that used in previous studies of variation in American Sign Language (Lucas, Bayley {\&} Valli 2001) and Australian Sign Language (Johnston {\&} Schembri 2006), with some differences that we discuss. The corpus consists of various kinds of texts collected with different strategies: free conversation (45 minutes), elicited dialogues (about 5-10 minutes), narration (10 minutes) and a picture-naming task (42 items). For the transcription we adopted the ELAN software (Johnston {\&} Crasborn 2006). Finally, a brief report on some preliminary results is presented.} } @inproceedings{hanke:10047:sign-lang:lrec, author = {Hanke, Thomas and K{\"o}nig, Lutz and Wagner, Sven and Matthes, Silke}, title = {{DGS} {Corpus} {\&} {Dicta-Sign}: The {Hamburg} Studio Setup}, pages = {106--109}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10047.html}, abstract = {Not taking into account budget restrictions, the setup of a sign language studio always is a balancing act between high quality recordings on the one hand not to make the transcription process even more complicated than it is anyway and possibly to enable automatic processing of the recordings, and on the other hand an environment where the informants still feel comfortable enough so that the recording situation does not have too much impact on the signing. In the case of the DGS Corpus project, an additional constraint is that the studio is to be relocated twelve times over the course of two years as it was decided to make the recordings in the regions instead of inviting participants to one central place to avoid dialectal mixing. One of the implications of this approach is that the studio is operated by non-specialist deaf fieldworkers with limited time available for training. \par Basically all tasks in the project involve two informants interacting in different ways with each other. A moderator (the fieldworker from the region) introduces the tasks and observes the conversation, but only interferes with the conversation if absolutely necessary. \par The camera setup we finally ended up with consists of seven cameras altogether, three on each informant and one for the whole scene including the moderator. Two HD cameras on the informant provide frontal and birds-eye views while a stereo camera mounted on top of the frontal-view camera provides footage that helps automatic processing. The seventh camera is an HD camera as well. \par In contrary to setups in earlier projects, we invite the two informants to sit down directly facing each other, with the frontal-view camera positioned above (and behind) the head of the other informant. Pre-tests revealed that with a distance of approximately three meters, the distorsion introduced by the elevated position of the camera does not negatively affect the transcription from video. Instead, this setting provides a front view of the informant similar to the addressee's, allowing to identify body shifts as well as direction of eye gaze more easily. At the same time, this constellation avoids informants targeting their signing back and forth between the addressee and the camera. \par Elicitation material and instructions are presented to the informants on screens located on the floor between them. A custom software, ``Session Director'' allows the moderator to present slides to the informants by the click of a button, and to keep track of the time elapsed for each individual task as well as the whole session. Using pre-recorded instructions and elicitation materials not only reduces the burdens on the moderator, but also makes sure that all informants get exactly the same input. \par Session Director keeps a log of all actions started by the moderator, allowing us to exactly reconstruct what task has been worked on when. This log is easily converted into tagging in our transcription environment, iLex. This not only allows automatic segmentation of tasks and pauses, but also introduces links from the transcript to the task and vice versa. \par Task descriptions for Session Director are kept as XML files, making it easy to use this freely available tool for other projects as well.} } @inproceedings{hochgesang:10055:sign-lang:lrec, author = {Hochgesang, Julie A. and Pascual-Villanueva, Pedro and Mathur, Gaurav and Lillo-Martin, Diane}, title = {Building a Database while Considering Research Ethics in Sign Language Communities}, pages = {112--115}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10055.html}, abstract = {We are constructing an American Sign Language ID-gloss Database, which will enable sign language researchers and Deaf community members to access standard glosses for common signs. Since we are working with a language used by a community that has historically been marginalized during the research process, we feel the need to include an ethical framework for working with the Sign Language community as we consider best practices for developing sign language corpora. We will refer to the guidelines, Sign Language Communities' Terms of Reference (SLCTR), outlined in Harris, Holmes {\&} Mertens (2009). Before making the database available to the ASL community, we plan to evaluate how members will use it and what they need from the research team to facilitate such use. This evaluation will go a long way towards ensuring that ownership of the research data lies with the ASL community. Such a reflexive evaluation of ethical practices is crucial from the beginning stages and throughout the research process. This means the ASL community is directly involved in the research process, is able to access aspects of the entire process, and can have a hand in the construction of knowledge about their own language, community and culture.} } @inproceedings{matthes:10019:sign-lang:lrec, author = {Matthes, Silke and Hanke, Thomas and Storz, Jakob and Efthimiou, Eleni and Dimou, Athanasia-Lida and Karioris, Panagiotis and Braffort, Annelies and Choisier, Annick and Pelhate, Julia and Safar, Eva}, title = {Elicitation tasks and materials designed for {Dicta-Sign}'s multi-lingual corpus}, pages = {158--163}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10019.html}, abstract = {Within the framework of the Dicta-Sign project, parallelised sign language corpora are being compiled for four European sign languages (BSL, DGS, GSL, and LSF). The aim for the data collection was to achieve as high a level of naturalness as can be achieved with semi-spontaneous utterances under lab conditions. Therefore, informants were filmed in pairs interacting with each other. With respect to parallelisability, elicitation tasks had to be designed that result in semantically close answers without predetermining the choice of vocabulary and grammar. \par The domain selected for Dicta-Sign is `Travel across Europe'. The tasks developed within the project cover different interaction formats ranging from monologues to sequences of very short turns, also with different levels of predictability. They include communication for transport by different means and contexts as well as related personal experiences. The elicitation materials are of different media formats and at various levels of complexity. They comprise of town and transportation network maps, pictures displaying a variety of places, items and situations linked to the target domain, as well as stories presented in sign language or as a picture story. In each session ten different tasks are to be performed, each of them planned to have a duration of about five to ten minutes, thereby switching roles between the informants several times during a recording session. \par Taking into account cultural differences as well as language dependent issues regarding the different countries in the project, the material was designed in a way that only minor adjustments are needed that do not change the character of a task. The elicitation tasks and materials developed within the project as well as experiences gained adjusting and using the material for Dicta-Sign's different target languages are illustrated in this paper.} } @inproceedings{nishio:10026:sign-lang:lrec, author = {Nishio, Rie and Hong, Sung-Eun and K{\"o}nig, Susanne and Konrad, Reiner and Langer, Gabriele and Hanke, Thomas and Rathmann, Christian}, title = {Elicitation methods in the {DGS} ({German} {Sign} {Language}) Corpus Project}, pages = {178--185}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10026.html}, abstract = {The DGS Corpus Project is a long-term project with two major aims: (i) to establish an extensive corpus of DGS and (ii) to develop a comprehensive dictionary of DGS-German based on the analysis of the corpus data. During the first three years the main focus is on data collection. Before setting up the corpus design we conducted a survey to get an overview on the existing elicitation materials. The design of our data collection contains a variety of different stimuli and tasks with the special attention to free conversation, dialogues and monologues. To this effect, a range of possible discourse modes were considered: narration and renarration, discussion, report and description. The stimuli include pictures, picture stories, non-verbal film clips (e.g. cartoons and realistic film clips) and signed movies. In order to minimize the influence of the surrounding spoken/written language, written German is not used if possible. Introduction and explanation of each task is provided in DGS in form of movie clips. All tasks were tested in a pilot phase to examine their feasibility and reliability. Some of the tasks tested needed to go through several rounds of modifications while others did not work at all and thus were excluded from the data collection. In this paper, we not only present the tasks for elicitation and stimuli, but also describe their development process. We also discuss reasons why some stimuli were adopted from other projects while others had to be developed specifically for the purpose of our project.} } @inproceedings{vendrame:10018:sign-lang:lrec, author = {Vendrame, Mara and Tiotto, Gabriele}, title = {{ATLAS} Project: Forecast in {Italian} {Sign} {Language} and Annotation of Corpora}, pages = {239--242}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10018.html}, abstract = {The paper presents the preliminary results of a research project focused on the creation and the annotation of one Italian Sign Language corpus concerning the weather forecasts domain. As a result of the annotation process, our annotations of signs sequences showed that the semantics of the signed discourse cannot be grasped just through an annotation of single weather signs which exploits the five parameters handshape, movements, directions, locations and non-manual components. Rather, from the annotation process appears that, in order to grasp the discourse semantics, it is necessary to consider the extensive use of Highly Iconic Structures in order to specify the iconic properties of the different atmospherics phenomena. In particular, it often occurs that several signs are combined among themselves (see also Cuxac, 2000; Di Renzo, et al, 2006; Pizzuto et al., 2008; Pizzuto, Rossini {\&} Russo, 2006). Thus, respect to single signs, our analysis of complex manual and non-manual units stored in our database suggests the necessity to better explore multidimensional aspects, in order to properly develop and train an automatic translator able to translate from Italian written text to Italian Sign Language.} } @inproceedings{schnepp:10007:sign-lang:lrec, author = {Schnepp, Jerry and Wolfe, Rosalee and McDonald, John C.}, title = {Synthetic Corpora: A Synergy of Linguistics and Computer Animation}, pages = {217--220}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10007.html}, abstract = {Synthetic corpora are computer representations of linguistic phenomena. They enable the creation of computer-generated animations depicting sign languages and are the complement of corpora containing videotaped exemplars. \par Synthetic corpora have the potential to serve multiple disciplines. They can aid in the automatic recognition of sign, because they contain the geometric data required for intelligent visual detection algorithms. Synthetic corpora can also provide visual depictions of abstract representations and act as a verification tool for data integrity and hypothesis testing. \par Because the signs are synthesized, not retrieved, they can be modified as they are formed. This provides the flexibility to generate an endless variety of utterances not possible with recordings, thus opening possibilities for automatic translation efforts. While representing sign for this purpose is still an open question, a synthetic corpus has the potential to serve in this capacity. The flexibility of synthetically-generated sign is also useful for the development of interpreter training software and self-directed learning tools for deaf children. \par By necessity, linguistics and computer animation must play a role in the creation of such corpora, as any corpus will need to serve both disciplines. At first glance, the goals of these disciplines would appear to be at cross purposes. Linguistics researchers often use corpora to form hypotheses through queries on linguistic features. Thus the corpora must encode such general abstractions as handshape, position, motion, palm orientation and non-manual signals. In contrast, creating computer animations of sign requires voluminous and detailed data, as the resulting animations must be realistic enough to pass the scrutiny of fluent signers. \par In actuality, the fields of linguistics and computer animation create a mutually beneficial synergy. Having the detailed precision required for animation can facilitate the exploration of subtle interactions among linguistic phenomena. Likewise, animators need an abstract representation to organize, combine, and synthesize complex animation data. \par Regardless of the animation technique, linguistic knowledge is necessary to produce any synthetic corpus. Animators who hand-transcribe need to work closely with linguists, so that the gloss is tagged correctly. Linguistic information guides the transcription artist's efforts to produce a natural exemplar that encapsulates the essential motions of a sign. With motion capture, the role of linguistics is no less central. Motion capture equipment generates massive amounts of data that must be cleaned to remove extraneous noise. The linguistic attributes of a sign give the cleanup artists precisely what they need to process and extract the desired motion. \par Our work thus far has focused on the creation of detailed and accurate animations of sign. The data that drive these animations have similarities to abstractions created by linguists. Thus, linguistic research guides the creation of a framework for automated sign synthesis. \par This presentation will examine several linguistic processes and discuss an approach to their representation in a synthetic corpus, including co-occurrence in nonmanual signals. This will include a demonstration of computer-generated American Sign Language.} } @inproceedings{brashear:10028:sign-lang:lrec, author = {Brashear, Helene and Zafrulla, Zahoor and Starner, Thad and Hamilton, Harley and Presti, Peter and Lee, Seungyon}, title = {{CopyCat}: A Corpus for Verifying {American} {Sign} {Language} During Game Play by Deaf Children}, pages = {27--32}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10028.html}, abstract = {The CopyCat project was designed to develop an interactive educational adventure game to help deaf children acquire language skills. The main goals of the project are to improve the language and memory abilities of deaf signing children, advance basic research in computer-based sign language recognition, and design an efficient language interaction model in order to assist in the language learning of deaf children. The CopyCat project was begun as a collaboration between Georgia Tech and the Atlanta Area School for the Deaf in 2004 and has been collecting ASL (American Sign Language) data since Spring of 2005. Since then we have collected 5829 signed phrases from over 30 children. \par In this paper we describe the evolution of the CopyCat system design, data collection methodology, and resulting corpus, as well as challenges and successes throughout the process.} } @inproceedings{cavender:10017:sign-lang:lrec, author = {Cavender, Anna and Cherniavsky, Neva and Chon, Jaehong and Ladner, Richard and Riskin, Eve and Vanam, Rahul and Wobbrock, Jacob}, title = {{MobileASL}: Overcoming the technical challenges of mobile video conversation in sign language}, pages = {45--48}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10017.html}, abstract = {As part of the ongoing MobileASL project, we have built a system to compress, transmit, and decode sign language video in real-time on an off-the-shelf mobile phone. In this work, we review the challenges that arose in developing our system and the algorithms we implemented to address them. Separate parts of this research have been previously published. \par Compression and transmission of sign language video presents unique difficulties. We must overcome weak processing power, limited bandwidth capacity, and low battery life. We also must ensure that the system is usable; that is, that the video is intelligible and the algorithms that we employ to save system resources do not irritate users. \par We describe the evolution of the MobileASL system and the algorithms we utilize to achieve real-time video communication on mobile phones. We first review our initial user studies to test feasibility and interest in video sign language on mobile phones. We then detail our three main challenges and solutions. To address weak processing power, we optimize the encoder to work on mobile phones, adapting a fast algorithm for distortion-complexity optimization to choose the best parameters. To overcome limited bandwidth capacity, we utilize a dynamic skin-based region of interest, which encodes the face and hands at a higher bit rate at the expense of the rest of the image. To save battery life, we automatically detect periods of signing and lower the frame rate when the user is not signing. \par We implement our system on off-the-shelf mobile phones and validate it through a user study. Fluent ASL signers participate in unconstrained conversations over the phones in a laboratory setting. They find the conversations with the dynamic skin-based region of interest more intelligible. The variable frame rate affects conversations negatively, but does not affect the users' perceived desire for the technology. \par Ongoing work includes varying the spatial resolution instead of the temporal resolution, further optimization of rate-distortion-complexity, and a field study to determine usability over a long period of time in a realistic setting.} } @inproceedings{collet:10058:sign-lang:lrec, author = {Collet, Christophe and Gonzalez, Matilde and Milachon, Fabien}, title = {Distributed System Architecture for Assisted Annotation of Sign Language Video Corpora}, pages = {49--52}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10058.html}, abstract = {This paper present one component of Dicta-Sign, a three-year FP7 ICT project that aims to improve the state of web-based communication for Deaf people. A part of this project is the annotation of sign language corpora. To improve the annotation task in terms of reproducibility and time consuming, several plug-ins for sign language video processing are developed. The component presented in this paper aims to link several plug-ins to annotation software through the network. These plug-ins can be coded in different languages, operating systems and computers. For that, it uses the SOAP Web-service and a specific data-format in XML for the data exchange.} } @inproceedings{crasborn:10021:sign-lang:lrec, author = {Crasborn, Onno and Sloetjes, Han}, title = {Using {ELAN} for annotating sign language corpora in a team setting}, pages = {61--64}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10021.html}, abstract = {ELAN is a multimedia annotation tool that is employed in many sign language corpus projects. It is a standalone desktop application that, like many other desktop applications, principally is a single user, document oriented application. In many scenarios this is still perfectly satisfactory but in large-scale corpus projects, involving many collaborators who are working on the same documents, the problem arises of how to resolve edit conflicts and how to prevent undesirable modifications to parts of the document. The Corpus NGT project is such a project and this paper describes the challenges that arose in the process of its creation as well as in the exploitation of this large collection of annotation documents. It outlines recent and possible future development of ELAN and alternate solutions that have been explored and applied.} } @inproceedings{hanke:10056:sign-lang:lrec, author = {Hanke, Thomas and Storz, Jakob and Wagner, Sven}, title = {{iLex}: Handling Multi-Camera Recordings}, pages = {110--111}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10056.html}, abstract = {Until recently, sign language researchers were quite happy with just one or two views for each recording session. While ELAN allows the user to relate several media files to a transcript and to sync them, iLex just allows one single media container and relies on the container format, such as QuickTime, to group and sync several video streams into one container. In order to save screen real estate, iLex offers the user the possibility to switch on or off individual tracks within the media file. This works quite fine with two or three different views grouped, but fails to provide an adequate solution in multi-view projects such as Dicta-Sign or DGS Corpus with seven cameras altogether for a pair of informants. The advent of HD videos makes screen real estate really an issue: Even on very large screens, video competes with transcription space. \par Here we present a user interface study that allows flexible switching between video layouts whenever the transcription focus changes. Switching (including zooming and cropping) may be initiated at any point of time by the user, or can be automated to depend on tagging such as tasks or turns. This user interface is backed up by a server infrastructure providing videos in different spatial resolutions as needed for optimal display while saving transfer bandwidth and local processing power which even nowadays becomes an issue when dealing with several HD videos in parallel.} } @inproceedings{hofmann:10010:sign-lang:lrec, author = {Hofmann, Markus and Goslin, Kyle and Nolan, Brian and Leeson, Lorraine and Sheikh, Haaris}, title = {Development of a {Moodle} {VLE} Plug-in to Support Simultaneous Visualisation of a Collection of Multi-Media Sign Language Objects}, pages = {116--120}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10010.html}, abstract = {Using Virtual Learning Environments (VLE) to support blended learning is very common in educational institutes. Delivering learning material in a flexible and semi-structured manner to the learner transforms such systems into powerful eLearning tools. However, the presentation and visualisation of individual or multiple learning objects is mostly dictated by the system and cannot be altered easily. \par This paper reports on a project between Trinity College Dublin (TCD) and the Institute of Technology Blanchardstown (ITB) that aims to improve the simultaneous visualisation of multiple multimedia objects for deaf learners of ISL. The project was implemented using the Open Source VLE Moodle. Moodle's nature of being Open Source and having the ability to code plug-ins qualified it to be the most suited vehicle to address the visualisation problem. Traditionally VLEs allow the viewing of one learning object at a time, which meant that deaf learners could either view a pre-recorded, signed in ISL, video lecture or concentrate on textual accompanying content but not both. The developed Moodle plug-in allows academics to group multiple videos into a 'lecture'. It further facilitates the addition of rich text content to each video. The learner can select and view one video from a possible sequence of many as well as view the text that belongs to the video. The paper further outlines detailed implementation and techniques applied.} } @inproceedings{huenerfauth:10030:sign-lang:lrec, author = {Huenerfauth, Matt and Lu, Pengfei}, title = {Eliciting Spatial Reference for a Motion-Capture Corpus of {American} {Sign} {Language} Discourse}, pages = {121--124}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10030.html}, abstract = {The goal of our research is to identify computational models of the referential use of signing space and of spatially inflected verb forms for use in American Sign Language (ASL) animations for accessibility applications for deaf users. This paper describes our collection and annotation of an ASL motion-capture corpus to be analyzed for our research. A study was conducted to compare alternative prompting strategies for eliciting single-signer multi-sentential ASL discourse that maximizes the use of pronominal spatial reference yet minimizes the use of classifier predicates, spatially complex ASL phenomena that are not the focus of our current research.} } @inproceedings{masneri:10015:sign-lang:lrec, author = {Masneri, Stefano and Schreer, Oliver and Schneider, Daniel and Tsch{\"o}pel, Sebastian and Bardeli, Rolf and Bordag, Stefan and Auer, Eric and Sloetjes, Han and Wittenburg, Peter}, title = {Towards semi-automatic annotation of video and audio corpora}, pages = {150--153}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10015.html}, abstract = {AVATecH (Advancing Video/Audio Technology in Humanities Research) is a project in which two Fraunhofer Institutes and two Max Planck Institutes collaborate in order to promote the development and application of technology for semi-automatic annotation of digital audio and video recordings. One of the aims of the AVATecH project is to implement algorithms that allow for the automatic or semi-automatic creation of pre-annotations for the video corpora, hence reducing the time needed to perform the manual annotation task. Due to the huge size of the corpora, and the extreme variety of the video content, the algorithms developed need to be fast, efficient and robust. In this paper we will present some of the algorithms currently under development, the modifications applied in order to get them working with large video corpora and how the results of the annotations are stored, as well as how they can be integrated in ELAN annotation software.} } @inproceedings{moreau:10045:sign-lang:lrec, author = {Moreau, C{\'e}dric and Mascret, Bruno}, title = {Organizing data in a multilingual observatory with written and signed languages}, pages = {168--171}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10045.html}, abstract = {The Acadmie Fran{\c c}aise institution is assigned and devoted to defending the French language and to making it a common heritage for all French speakers. The French Sign Language (LSF) has never had such a support. To face this situation, a reference tool has been created, supported by the French Ministry of Education and by the General Delegation to the French language and to languages of France. This tool is a collaborative website entirely bilingual French and LSF, and which proposes for each concept at least one definition and its associated descriptors in various knowledge fields. Before being spread on-line, the information given by users (text, picture, video, presentation) is examined by experts on form and content, and is validated or rejected by these experts with an explanation. \par Considering regional and sociological differences, several signs may be proposed and validated for one concept. Our project does not wish to choose the ''ideal sign'', but wants to submit to our identified users all the proposals and to list their comments (have they come across this sign and if so, in which context). A set of information is thus collected for each sign and can be related to users profiles. The website is therefore an exchange platform, but can also be used as a linguistics observatory. \par One of our main issues concerning the data organization was to manage to adjust users different viewpoints and different uses of the website. Indeed, our platforms goal is not to make a simple dictionary but to create a network of ontologies. Our other issue is now that we cannot use a rigid organization model, because our website must constantly evolve and include new concepts and new descriptions or functionalities, such as illustrations, homonyms, antonyms, etc. In this article we will first briefly describe our platforms goals, then present our specific data organization which allows for example several classifications to be used simultaneously. We will illustrate this approachs interest with a critic of Deweys classification, that we had at first implemented despite its limits (acceding to a precise concept is difficult, the organization is not intuitive, recent concepts or specific LSF concepts cannot be referenced, etc.). We will propose to replace it with classifications directly created by our users and corresponding to their expectations and needs. This way the tree diagram is built gradually and supervised by experts in each knowledge field. \par Each content thus goes with descriptors and classifiers allowing it to play different parts depending on the context. Therefore a content can at the same time be a concept, a classification theme or sub-theme, or an illustration -- the context will mobilize the appropriate contents depending on their descriptors and classifiers. We will finally present our current work on integrating direct resources in LSF through descriptors defining a sign's spatial position and its moves (hands, body and face), in order to highlight our platforms great ability to evolve. We will also show that this data organization allows an easy conversion to other countries sign languages.} } @inproceedings{tanaka:10034:sign-lang:lrec, author = {Tanaka, Saori and Matsusaka, Yosuke and Nakazono, Kaoru}, title = {Development of E-Learning Service of Computer Assisted Sign Language Learning: Online Version of {CASLL}}, pages = {231--234}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10034.html}, abstract = {In this study, we introduce the problems for realizing an e-learning system available online and outline some ethical issues behind these problems. The difficulties faced to us, when we were going to open Computer Assisted Sign language Learning (CASLL) system online, were one to expose the sign language movies to public with downloadable way, one for increasing the course materials, and one to enhance the collaboration between learners. The ethical discussions revealed that the reliability for the system and the collaborative work for expand the number of course materials were necessary for overcoming the difficulties. In order to realize the reliable and the collaborative e-learning system, we implemented CASLL within Moodle, an open-source Course Management System. For re-designing the system to actual use for sign language learners and teachers, we added new functions to Moodle; the protection function for the right of publicity, the wiki function to enable collaborative course editing and finally the Link function to enhance public relations. We are going to evaluate the system design from the view point of the usability for teaching, the effectivity for learning, and the utility for collaboration.} } @inproceedings{campr:10043:sign-lang:lrec, author = {Campr, Pavel and Hr{\'u}z, Marek and Langer, Ji{\v r}{\'i} and Kanis, Jakub and {\v Z}elezn{\'y}, Milo{\v s} and M{\"u}ller, Lud{\v e}k}, title = {Towards {Czech} on-line sign language dictionary -- technological overview and data collection}, pages = {41--44}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10043.html}, abstract = {In this article we present the current state of our work on an on-line sign language dictionary. The aim is to create both an explanatory and a translation dictionary. It is primarily targeted (but not limited) to the Czech and Czech sign language. At first we describe technological aspects of the dictionary and then our data collection practices. The dictionary is an on-line application build with respect to the linguistic needs. We use written text to represent spoken languages and several representations are supported for sign languages: videos, images, HamNoSys, SignWriting and interactive 3D avatar. To decrease time required for data collection and publishing in the dictionary we use computer vision methods for video analysis to detect sign boundaries and analyze the manual component of performed sign for automatic categorization. The content will be created by linguists using both new and already existing data. Then, the dictionary will be opened to the public with possibility to add, modify and comment data. We expect that this possibility of on-line elicitation will increase the number of informants, cover more regions and makes the elicitation cheaper and the evaluation easier. Furthermore we prepare a mobile interface of the dictionary. The mobile interface will use different format of web pages and different video compression methods optimized for slower Internet connection. We also prepare an offline version of the dictionary which can be automatically generated from the online content and downloaded for offline usage.} } @inproceedings{duarte:10020:sign-lang:lrec, author = {Duarte, Kyle and Gibet, Sylvie}, title = {Corpus Design for Signing Avatars}, pages = {73--75}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10020.html}, abstract = {The SignCom project uses motion capture (mocap) data to animate a virtual French Sign Language (LSF) signer. An important part of any signing avatar project is to ensure that a computer animation engine has a large quantity of interesting and on-topic signs from which to build novel signing sequences. In this article, we detail the process of selecting an adequate range of signs and situations to be included in our corpus: from controlling discourse topic to including signs that can accept modified movements or handshapes, we describe how an avatar corpus has a different motivation than traditional signed language corpora.} } @inproceedings{elliott:10035:sign-lang:lrec, author = {Elliott, Ralph and Bueno, Javier and Kennaway, Richard and Glauert, John}, title = {Towards the Integration of Synthetic {SL} Animation with Avatars into Corpus Annotation Tools}, pages = {84--87}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10035.html}, abstract = {We outline the main features of our synthetic virtual human sign language system, JASigning. We describe how we have extended its input notation, SiGML, to allow explicit control of performance time, and we describe our initial steps on the path to integrating virtual human sign language performance into annotation tools, where it may be compared with video depicting the corresponding real human performance.} } @inproceedings{filhol:10003:sign-lang:lrec, author = {Filhol, Michael and Delorme, Maxime and Braffort, Annelies}, title = {Combining constraint-based models for Sign Language synthesis}, pages = {88--91}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10003.html}, abstract = {The framework is that of Sign Language synthesis by virtual signers. In this paper, we present a sign generation system using a variety of input layers, separated on two sides: an anatomical side and a linguistic side. In a first part we suggest a way of implementing the flexibility required by Sign Languages into the system by using combinations of necessary and suficient constraints. The anatomical side of the input specifies all morphological and articulatory constraints that model the behaviour of a human skeleton, while the linguistic input specifies language constraints (lexical, grammatical, iconic...) that must be applied to the signer's body to utter the correct sign sequence. A second part explains how to combine all these parts of the input in a conjunction of constraints for each time frame of the animation. A point is made that conflicting constraints may be given but that they need be prioritised in order still to decide on acceptable solutions. A first idea of a global priority order is given to illustrate this issue.} } @inproceedings{goulas:10008:sign-lang:lrec, author = {Goulas, Theodoros and Fotinea, Stavroula-Evita and Efthimiou, Eleni and Pissaris, Michalis}, title = {{SiS-Builder}: A Sign Synthesis Support Tool}, pages = {102--105}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10008.html}, abstract = {Here we will present research work performed in the framework of the DICTA-SIGN project, closely related to Sign Language Synthesis and Animation and especially intended to cover for the need of creating lexical resources and evaluating them when performed by a signing avatar. Along these lines, a tool has been created to automatically generate SiGML transcriptions of any given HamNoSys string, as well as the relevant transcription file, by providing the HamNoSys characters of a sign. \par Users are allowed to create a phrase of up to 4 sign units, by introducing the corresponding HamNoSys notations in a sequence of appropriate fields. The related xml script is then automatically created, allowing also for on demand storage on the server. \par The here reported tool is web based, accessible by everyone, and allows users to interact with it without any special installations on the client side. Users may register, but this is not mandatory for use of the tool. Registered members can save their created scripts on the server in contrary to the non registered ones. Online and offline manuals are available to the users as well as a FAQ facility. \par As regards further tool functionalities, users are also enabled to see the HamNoSys notation of a sign chosen from a validated list of lemmas or by entering the raw xml script in the proper field. Users are able to switch between SiGML data and HamNoSys notations on an instant by just selecting the wished function. This way, it is possible to test/ see the results of creation of a lexical item, either by consulting the HamNoSys sequence, for those familiar with the HamNoSys syntax, or by animating the results through the avatar with the use of the SiGML script. \par Users can create HamNoSys sequences by choosing the proper selection on the menu. This is a new feature, enhancing the tool's functionalities, added -upon completion of an evaluation phase- to allow users to create HamNoSys strings on line and then proceed with automatic creation of the corresponding SiGML scripts. \par Furthermore, along with the HamNoSys manual characters, users may add non manual characters to the creation of the SiGML script. If needed, users may add more than one movement of a particular body part, i.e. head or shoulders, to make animation look closer to natural signing. \par The final step is creation of the script. The user is then able to copy and paste the script to the avatar page to visualise the results of the created sequence, the latter been performed by the avatar. \par Registered users are able to maintain/modify the data created by them. \par The tool is based on open source internet technologies for easy access and compatibility. Technologies that have been used are mostly "php" and "java script".} } @inproceedings{jennings:10011:sign-lang:lrec, author = {Jennings, Vince and Elliott, Ralph and Kennaway, Richard and Glauert, John}, title = {Requirements for a Signing Avatar}, pages = {133--136}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10011.html}, abstract = {We present the technical specification for an avatar that is compliant with Animgen, the synthetic signing engine used at the University of East Anglia for generating deaf signing animations. The specification will include both the basic definition required for any standard animating avatar, and the additional parameters that Animgen requires to generate signing. Avatars compatible with Animgen are created using the ARPToolkit, an application developed at UEA that has a plug-in architecture for tools that are used for rigging an avatar mesh for animation. The toolkit also generates the additional data needed by Animgen for each avatar.} } @inproceedings{krnoul:10042:sign-lang:lrec, author = {Kr{\v n}oul, Zden{\v e}k}, title = {New features in synthesis of sign language addressing non-manual component}, pages = {143--146}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10042.html}, abstract = {A sign language synthesis system converts previously noted signs into the computer animation. The animation is created using a specially designed 3D model of the human figure and algorithms transferring the sign to movements of the model. In principle the sign language contains both the non-manual component (shape and movement of hands) and the non-manual component (facial movements, etc.). Notation of the non-manual component was not yet sufficiently explored in terms of an automatic conversion to the animation. In the article we describe both notation methodology of the non-manual component and technical aspects for conversion of symbols to movements of the animation model. In addition an appropriate animation method for the 3D shape of face is assumed. The result is an extended notation supplementing notation of the manual component with the non-manual component. The extended notation preserves the feasibility of an automatic conversion and keeps the original level of generality. In connection with the methodology we present the notations of the basic types of non-manual components of the Czech sign language.} } @inproceedings{sansegundo:10012:sign-lang:lrec, author = {San-Segundo, Rub{\'e}n and L{\'o}pez, Ver{\'o}nica and Mart{\'i}n, Raquel and S{\'a}nchez, David and Garc{\'i}a, Adolfo}, title = {Language Resources for {Spanish} - {Spanish} {Sign} {Language} ({LSE}) Translation}, pages = {208--211}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10012.html}, abstract = {This paper describes the first Spanish-Spanish Sign Language (LSE) parallel corpus for language processing research focused on specific domains. This corpus includes more than 4,000 Spanish sentences translated into LSE. For every sentence, there is a video with the sign language representation. These sentences are focused on two restricted domains (two personal services): the renewal of the Identity Document and Driver's License. This corpus has been obtained with the collaboration of Local Government Offices where these services are provided. Over several weeks, the most frequent explanations (from the government employees) and the most frequent questions (from the user) were taken down. \par This corpus also contains more than 800 sign descriptions in several sign-writing specifications: in glosses, SEA (Sistema de Escritura Alfab{\'e}tica) (Herrero, 2004), HamNoSys (Prillwitz et al, 1989), and SIGML (Zwiterslood et al, 2004) (a link to a text file with the SIGML description necessary for representing the sign with the eSIGN avatar: http://www.sign-lang.uni-hamburg.de/esign/). These descriptions have been generated with a modified version of the eSign Editor. This new version includes a graph to phoneme system for Spanish and a SEA- HamNoSys converter. \par These language resources have been very important for the research project developed by Universidad Polit{\'e}cnica de Madrid and Fundaci{\'o}n CNSE (Spanish Association of Deaf People) during the last three years (www.traduccionvozlse.es). The main target of this project has been to develop an advanced communication system for Deaf including two translation modules: The first one is a Spanish into LSE translation module. This first module is made up of a speech recognizer (for decoding the spoken utterance into a word sequence), a natural language translator (for converting a word sequence into a sequence of signs belonging to the sign language), and a 3D avatar animation module (for playing back the signs). The second module is a Spanish generator from LSE. This module consists of a visual interface (where a deaf person can specify a sequence of signs in sign-writing), a language translator (for generating the sequence of words in Spanish), and finally, a text to speech converter. The visual interface allows a sign sequence to be defined using several sign-writing alternatives. \par For language translation, three technological alternatives were integrated and combined: an example-based strategy, a rule-based translation method and a statistical translator.} } @inproceedings{borgotallo:10053:sign-lang:lrec, author = {Borgotallo, Roberto and Marino, Carmen and Piccolo, Elio and Prinetto, Paolo and Tiotto, Gabriele and Rossini, Mauro}, title = {A Multilanguage Database for supporting Sign Language Translation and Synthesis}, pages = {23--26}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10053.html}, abstract = {The design of a language database is an important task within projects targeting sign language research. In this paper is presented a database structure that supports both linguistic information and visualisation oriented data to assist a final publication of services for deaf people. The database has been designed within the Automatic Translation into sign LAnguageS (ATLAS) project that takes aim at getting the automatic translation from written Italian to Italian Sign Language (LIS). The final step of the overall process is the enrichment of the original video with a superimposed virtual character realised by 3D animated computer graphics. The top element within the database is the A{\_}Product defined as the main primitive element managed by the ATLAS platform under which all the other data, from input sources to the final publication modalities and attributes lay. The A{\_}Product includes the reference to the original content and all the intermediate elaborations results towards the final publication comprehensive of the virtual character animations. Among the others, the most important transformation is the automatic translation from a written Italian text to the intermediate language AEWLIS (ATLAS Extended Written LIS), formalized within the ATLAS project.} } @inproceedings{athitsos:10022:sign-lang:lrec, author = {Athitsos, Vassilis and Neidle, Carol and Sclaroff, Stan and Nash, Joan and Stefan, Alexandra and Thangali, Ashwin and Wang, Haijing and Yuan, Quan}, title = {Large Lexicon Project: {American} {Sign} {Language} Video Corpus and Sign Language Indexing/Retrieval Algorithms}, pages = {11--14}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10022.html}, abstract = {When we encounter a word that we do not understand in a written language, we can look it up in a dictionary. However, looking up the meaning of an unknown sign in American Sign Language (ASL) is not nearly as straightforward. This paper describes progress in an ongoing project aiming to build a computer vision system that helps users look up the meaning of an unknown ASL sign. When a user encounters an unknown ASL sign, the user submits a video of that sign as a query to the system. The system evaluates the similarity between the query and video examples of all signs in the known lexicon, and presents the most similar signs to the user. The user can then look at the retrieved signs and determine if any of them matches the query sign. \par An important part of the project is building a video database containing examples of a large number of signs. So far we have recorded at least two video examples for almost all of the 3,000 signs contained in the Gallaudet dictionary. Each video sequence is captured simultaneously from four different cameras, providing two frontal views, a side view, and a view zoomed in on the face of the signer. Our entire video dataset is publicly available on the Web. \par Automatic computer vision-based evaluation of similarity between signs is a challenging task. In order to improve accuracy, we manually annotate the hand locations in each frame of each sign in the database. While this is a time-consuming process, this process incurs a one-time preprocessing cost that is invisible to the end-user of the system. At runtime, once the user has submitted the query video, the current version of the system asks the user to specify hand locations in the first frame, and then the system automatically tracks the location of the hands in the rest of the query video. The user can review and correct the hand location results. Every correction that the user makes on a specific frame is used by the system to further improve the hand location estimates in other frames. \par Once hand locations have been estimated for the query video, the system evaluates the similarity between the query video and every sign video in the database. Similarity is measured using the Dynamic Time Warping (DTW) algorithm, a well-known algorithm for comparing time series. The performance of the system has been evaluated in experiments where 933 signs from 921 distinct sign classes are used as the dataset of known signs, and 193 signs are used as a test set. In those experiments, only a single frontal view was used for all test and training examples. For 68{\%} of the test signs, the correct sign is included in the 20 most similar signs retrieved by the system. \par In ongoing work, we are manually annotating hand locations in the remainder of our collected videos, so as to gradually incorporate more signs into our system. We are also investigating better ways for measuring similarity between signs, and for making the system more automatic, reducing or eliminating the need for the user to manually provide information to the system about hand locations.} } @inproceedings{michael:10029:sign-lang:lrec, author = {Michael, Nicholas and Neidle, Carol and Metaxas, Dimitris}, title = {Computer-based recognition of facial expressions in {ASL}: from face tracking to linguistic interpretation}, pages = {164--167}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10029.html}, abstract = {Most research in the field of sign language recognition has focused on the manual component of signing, despite the fact that there is critical grammatical information expressed through facial expressions and head gestures. We, therefore, propose a novel framework for robust tracking and analysis of nonmanual behaviors, with an application to sign language recognition. \par Our method uses computer vision techniques to track facial expressions and head movements from video, in order to recognize such linguistically significant expressions. The methods described here have relied crucially on the use of a linguistically annotated video corpus that is being developed, as the annotated video examples have served for training and testing our machine learning models. We apply our framework to continuous recognition of three classes of grammatical expressions, namely wh-questions, negative expressions, and topics. \par Our method is signer-independent, utilizing spatial pyramids and Hidden Markov Models (HMMs) to model the temporal variations of facial shape and appearance.} } @inproceedings{buehler:10044:sign-lang:lrec, author = {Buehler, Patrick and Everingham, Mark and Zisserman, Andrew}, title = {Exploiting signed {TV} broadcasts for automatic learning of {British} {Sign} {Language}}, pages = {33--40}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10044.html}, abstract = {In this work, we will present several contributions towards automatic recognition of BSL signs from continuous signing video sequences. Specifically, we will address 3 main points: (i) automatic detection and tracking of the hands using a generative model of the image; (ii) automatic learning of signs from TV broadcasts of single signers, using only the supervisory information available from subtitles; and (iii) discriminative signer-independent sign recognition using automatically extracted training data from a single signer. \par Our source material consists of many hours of video with continuous signing and corresponding subtitles recorded from BBC digital television. This is very challenging material for a number of reasons, including self-occlusions of the signer, self-shadowing, blur due to the speed of motion, and in particular the changing background. \par Knowledge of the hand position and hand shape is a pre-requisite for automatic sign language recognition. We cast the problem of detecting and tracking the hands as inference in a generative model of the image, and propose a complete model which accounts for the positions and self-occlusions of the arms. Reasonable configurations are obtained by efficiently sampling from a pictorial structure proposal distribution. The results using our method exceed the state-of-the-art for the length and stability of continuous limb tracking. \par Previous research in sign language recognition has typically required manual training data to be generated for each sign, e.g. a signer performing each sign in controlled conditions - a time-consuming and expensive procedure. We show that for a given signer, a large number of BSL signs can be learned automatically from TV broadcasts using the supervisory information available from subtitles broadcast simultaneously with the signing. We achieve this by modelling the problem as one of multiple instance learning. In this way we are able to extract the sign of interest from hours of signing footage, despite the very weak and "noisy" supervision from the subtitles. \par Lastly, we will show how the automatic recognition of signs can be extended to multiple signers. Using automatically extracted examples from a single signer we train discriminative classifiers and show that these can successfully recognize signs for unseen signers. This demonstrates that our features (hand trajectory and hand shape) generalise well across different signers, despite the significant inter-personal differences in signing.} } @inproceedings{cooper:10039:sign-lang:lrec, author = {Cooper, Helen and Bowden, Richard}, title = {Sign Language Recognition using Linguistically Derived Sub-units}, pages = {57--60}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10039.html}, abstract = {This work proposes to learn linguistically-derived sub-unit classifiers for sign language. The responses of these classifiers can be combined by Markov models, producing efficient sign-level recognition. Tracking is used to create vectors of hand positions per frame as inputs for sub-unit classifiers learnt using AdaBoost. Grid-like classifiers are built around specific elements of the tracking vector to model the placement of the hands. Comparative classifiers encode the positional relationship between the hands. Finally, binary-pattern classifiers are applied over the tracking vectors of multiple frames to describe the motion of the hands. Results for the sub-unit classifiers in isolation are presented, reaching averages over 90{\%}. Using a simple Markov model to combine the sub-unit classifiers allows sign level classification giving an average of 63{\%}, over a 164 sign lexicon, with no grammatical constraints.} } @inproceedings{dreuw:10001:sign-lang:lrec, author = {Dreuw, Philippe and Forster, Jens and Gweth, Yannick and Stein, Daniel and Ney, Hermann and Mart{\'i}nez Ruiz, Gregorio and Verges Llahi, Jaume and Crasborn, Onno and Ormel, Ellen and Du, Wei and Hoyoux, Thomas and Piater, Justus and Moya Lazaro, Jos{\'e} Miguel and Wheatley, Mark}, title = {{SignSpeak} - Understanding, Recognition, and Translation of Sign Languages}, pages = {65--72}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10001.html}, abstract = {The SignSpeak project will be the first step to approach sign language recognition and translation at a scientific level already reached in similar research fields such as automatic speech recognition or statistical machine translation of spoken languages. Deaf communities revolve around sign languages as they are their natural means of communication. Although deaf, hard of hearing and hearing signers can communicate without problems amongst themselves, there is a serious challenge for the deaf community in trying to integrate into educational, social and work environments. The overall goal of SignSpeak is to develop a new vision-based technology for recognizing and translating continuous sign language to text. New knowledge about the nature of sign language structure from the perspective of machine recognition of continuous sign language will allow a subsequent breakthrough in the development of a new vision-based technology for continuous sign language recognition and translation. Existing and new publicly available corpora will be used to evaluate the research progress throughout the whole project.} } @inproceedings{efthimiou:10027:sign-lang:lrec, author = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Glauert, John and Bowden, Richard and Braffort, Annelies and Collet, Christophe and Maragos, Petros and Goudenove, Fran{\c c}ois}, title = {{DICTA-SIGN}: Sign Language Recognition, Generation and Modelling with application in Deaf Communication}, pages = {80--83}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10027.html}, abstract = {Here we present the components and objectives of the EU funded project DICTA-SIGN. Dicta-Sign (http://www.dictasign.eu) is a three-year research project that involves the Institute for Language and Speech Processing, the University of Hamburg, the University of East Anglia, the University of Surrey, LIMSI/CNRS, the Universit{\'e} Paul Sabatier, the National Technical University of Athens, and WebSourd. It aims to improve the state of web-based communication for Deaf people by allowing the use of sign language in various human-computer interaction scenarios. It researches and develops recognition and synthesis engines for signed languages, aiming at a level of detail necessary for recognizing and generating authentic signing. In this context, Dicta-Sign aims at developing several technologies demonstrated via a sign language-aware Web 2.0. \par Dicta-Sign supports four European sign languages: Greek. British, German, and French Sign Language and differs from previous work in that it aims to integrate tightly recognition, animation, and machine translation. All these components are informed by appropriate linguistic models from the ground up, including phonology, grammar, and non-manual features. \par Expected outputs of the project include:\begin{itemize}\item A parallel multi-lingual corpus for four national sign languages - German, British, French and Greek (DGS, BSL, LSF and GSL respectively),\item A substantial multilingual dictionary of at least 1000 signs for each represented sign language,\item A continuous sign language recognition system that achieves significant improvement in terms of coverage and accuracy of sign recognition in comparison with current technology; furthermore this system will research the novel directions of multimodal sign fusion and signer adaptation,\item A language generation and synthesis component, covering in detail the role of manual, non-manual and placement within signing space,\item Annotation tools which incorporate these technologies providing access to the corpus and whose long term utility can be judged by the up-take by other sign language researchers,\item Three bidirectional integrated prototype systems which show the utility of the system components beyond the annotation tools application,\item A showcase demonstrator which exhibits how integration of the different components can support user communication needs.\end{itemize}} } @inproceedings{forster:10038:sign-lang:lrec, author = {Forster, Jens and Stein, Daniel and Ormel, Ellen and Crasborn, Onno and Ney, Hermann}, title = {Best Practice for Sign Language Data Collections Regarding the Needs of Data-Driven Recognition and Translation}, pages = {92--97}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10038.html}, abstract = {We propose best practices for gloss annotation of sign languages taking into account the needs of data-driven approaches to recognition and translation of natural languages. Furthermore, we provide reference numbers for several technical aspects for the creation of new sign language data collections. Most available sign language data collections are of limited use to data-driven approaches, because they focus on rare sign language phenomena, or lack machine readable annotation schemes. Using a natural language processing point of view, we briefly discuss several sign language data collection, propose best practices for gloss annotation stemming from experience gained using two large scale sign language data collections, and derive reference numbers for several technical aspects from standard benchmark data collections for speech recognition and translation.} } @inproceedings{piater:10052:sign-lang:lrec, author = {Piater, Justus and Hoyoux, Thomas and Du, Wei}, title = {Video Analysis for Continuous Sign Language Recognition}, pages = {192--195}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10052.html}, abstract = {The recognition of continuous, natural signing is very challenging due to the multimodal nature of the visual cues (fingers, lips, facial expressions, body pose, etc.), as well as technical limitations such as spatial and temporal resolution and unreliable depth cues. On the other hand, signing gestures are designed to be robustly discernible. We therefore argue in favor of an integrative approach to sign language recognition that aims to extract sufficient aggregate information for robust sign language recognition, even if many of the individual cues are unreliable. Our strategy to implement such an integrated system currently rests on two modules, for which we will show initial results. The first module uses active appearance models for detailed face tracking, allowing the quantification of facial expressions such as mouth and eye aperture and eyebrow raise. The second module is dedicated to hand tracking using color and appearance. A third module will be concerned with tracking upper-body articulated pose, linking the face to the hands for increased overall robustness.} } @inproceedings{pitsikalis:10049:sign-lang:lrec, author = {Pitsikalis, Vassilis and Theodorakis, Stavros and Maragos, Petros}, title = {Data-Driven Sub-Units, Modeling Structure of Multiple Cues for Continuous Sign Language Recognition}, pages = {196--203}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10049.html}, abstract = {We investigate the automatic phonetic modeling of sign language based on phonetic sub-units, which are data driven and without any prior phonetic information. Visual processing is based on a probabilistic skin color model and a framewise geodesic active contour segmentation; occlusions are handled by a forward-backward prediction component leading finally to simple and effective region-based visual features. For sign-language modeling we propose a modeling structure for data-driven sub-unit construction. This utilizes the cue that is considered crucial to segment the signal into parts; at the same time we also classify the segments by implicitly assigning labels of Dynamic or Static type. This segmentation and classification step disentangles Dynamic from Static parts and allows us to employ for each type of segment the appropriate cue, modeling and clustering approach. The constructed Dynamic segments are exploited at the model level via hidden Markov models (HMMs). The Static segments are exploited via k-means clustering. Each Dynamic or Static part, exploits the appropriate cue related to the movement. We propose that the movement cues are normalized in order to be translation and scale invariant. We apply the proposed modeling for further combination of the movement trajectory individual cues. The proposed approaches are evaluated in recognition experiments conducted on the continuous sign language corpus of Boston University (BU-400) showing promising preliminary results.} } @inproceedings{serrano:10051:sign-lang:lrec, author = {Serrano, Marina and Gumiel, Jes{\'u}s and Moya Lazaro, Jos{\'e} Miguel}, title = {Automatic sign language recognition, translation: a social approach}, pages = {221--224}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10051.html}, abstract = {This paper reviews the social needs of the deaf community and describes the mechanisms and/or technologies which would improve the quality of life of this collective. The base of this project is a pilot of teleinterpretation developed in Andalusia (Spain), and as results of the interaction with the users, have been found two investigation lines, the telephone communication, and the e-learning. This activities have a clearly defined technology needs by hearing impaired, and the existing solutions do not fix completely the problem, so they are a good scenario to implement an automatic sing language recognition system. The aim of the paper is demonstrate how to thanks to this technology, social barriers can be torn down, allowing equal access to those services that today are restrictive for the collective of deaf people.} } @inproceedings{stein:10014:sign-lang:lrec, author = {Stein, Daniel and Forster, Jens and Zelle, Uwe and Dreuw, Philippe and Ney, Hermann}, title = {{RWTH-Phoenix}: Analysis of the {German} {Sign} {Language} Weather Forecast Corpus}, pages = {225--230}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10014.html}, abstract = {In this work, the recent additions to the RWTH-Phoenix corpus, a data collection of interpreted news announcement, are analysed. The corpus features videos, gloss annotation of German Sign Language and transcriptions of spoken German. The annotation procedure is reported, and the corpus statistics are discussed. We present automatic machine translation results for both directions, and discuss syntactically motivated enhancements.} } @inproceedings{agris:10006:sign-lang:lrec, author = {von Agris, Ulrich and Kraiss, Karl-Friedrich}, title = {{SIGNUM} Database: Video Corpus for Signer-Independent Continuous Sign Language Recognition}, pages = {243--246}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10006.html}, abstract = {Research in the field of continuous sign language recognition has not yet addressed the problem of interpersonal variance in signing. Applied to signer-independent tasks, current recognition systems show poor performance as their training bases upon corpora with an insufficient number of signers. In contrast to speech recognition, there is actually no benchmark which meets the requirements for signer-independent continuous sign language recognition. Because of this absence we created a new sign language corpus based on a vocabulary of 450 basic signs in German Sign Language (DGS). The corpus comprises 780 sentences each performed by 25 native signers of different sexes and ages. This database is now available for all interested researchers.} } @inproceedings{voskresenskiy:10031:sign-lang:lrec, author = {Voskresenskiy, Alexander and Ilyin, Sergey}, title = {About Recognition of Sign Language Gestures}, pages = {247--250}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10031.html}, abstract = {A motion capture technique for implementing sign language dictionary is described. Problems of perception and recognition of gestures of Russian sign language in system of the automated sign language translation are discussed. The new approach to morphology of gestures and a method for separate gestures in sign statements are offered. The working definition for "text understanding" is offered.} } @inproceedings{masso:10004:sign-lang:lrec, author = {Mass{\'o}, Guillem and Badia, Toni}, title = {Dealing with Sign Language Morphemes in Statistical Machine Translation}, pages = {154--157}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10004.html}, abstract = {The aim of this research is to establish the role of linguistic information in data-scarce statistical machine translation for sign languages using freely available tools. The main challenge in statistical machine translation is the scarcity of suitable data, and this problem becomes more pronounced in sign languages. The available corpora are small, usually not domain-specific, and their annotation conventions can vary considerably. Elaborating our own corpus is a very time-consuming task and the amount of data that we can obtain is even more reduced. Under these conditions, morpho-syntactic information helps to improve statistical machine translation results, but there are not linguistic processing tools for sign languages. We have managed to improve translations from Catalan to Catalan Sign Language by using factored models in an open source translation system with basic linguistic information such as the lemma or an annotation tier tag. Furthermore, this allows us to deal with sign language morphemes in a more systematic way.} } @inproceedings{morrissey:10032:sign-lang:lrec, author = {Morrissey, Sara and Somers, Harold and Smith, Robert and Gilchrist, Shane and Dandapat, Sandipan}, title = {Building Sign Language Corpora for Use in Machine Translation}, pages = {172--177}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10032.html}, abstract = {In recent years data-driven methods of machine translation (MT) have overtaken rule-based approaches as the predominant means of automatically translating between languages. A pre-requisite for such an approach is a parallel corpus of the source and target languages. Technological developments in sign language (SL) capturing, analysis and processing tools now mean that SL corpora are becoming increasingly available. With transcription and language analysis tools being mainly designed and used for linguistic purposes, we describe the process of creating a multimedia parallel corpus specifically for the purposes of English to Irish Sign Language (ISL) MT. As part of our larger project on localisation, our research is focussed on developing assistive technology for patients with limited English in the domain of healthcare. \par Focussing on the first point of contact a patient has with a GP{\'i}s office, the medical secretary, we sought to develop a corpus from the dialogue between the two parties when scheduling an appointment. Throughout the development process we have created one parallel corpus in six different modalities from this initial dialogue, namely English speech, English text, ISL videos, Bangla text, HamNoSys transcription and SiGML code. In this paper we discuss the multi-stage process of the development of this parallel corpus as individual and interdependent entities, both for our own MT purposes and their usefulness in the wider MT and SL research domains.} } @inproceedings{safar:10060:sign-lang:lrec, author = {Safar, Eva and Glauert, John}, title = {Sign Language {HPSG}}, pages = {204--207}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10060.html}, abstract = {We present an overview of some relevant aspects of sign language synthesis in the ViSiCAST project, which might serve as a possible basis for the Dicta-Sign project. Dicta-Sign is a 3-year EU-funded project, that undertakes parallel corpus collection in different Sign Languages (SLs) and fundamental research and development of sign recognition and generation techniques in order to open up new potential applications for sign language users. One of the aims in Dicta-Sign is to find a model that is suitable for both recognition and generation. In this paper we revisit the main aspects of the synthesis techniques implemented in ALE Prolog using a sign language specific HPSG with the view for future changes needed. We briefly describe the HPSG feature structure and the rules and principles of the grammar, which cover important SL phenomena like mode, prodrop, plurals, classifiers and signing space.} } @proceedings{lrec:sign-lang:08, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, title = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, url = {http://www.lrec-conf.org/proceedings/lrec2008/workshops/W25_Proceedings.pdf} } @inproceedings{alvarezsanchez:08008:sign-lang:lrec, author = {{\'A}lvarez S{\'a}nchez, Patricia and B{\'a}ez Montero, Inmaculada C. and Fern{\'a}ndez Soneira, Ana}, title = {Linguistic, Sociological and Technical Difficulties in the Development of a {Spanish} {Sign} {Language} ({LSE}) Corpus}, pages = {9--12}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08008.html}, abstract = {The creation of a Spanish Sign Language corpus has been, since 1995 until 2000, one of the main aims of our Sign Languages Research Group at the University of Vigo. As a result of this attempt, these are some of our publications: \par B{\'a}ez Montero, I. C. {\&} M. C. Cabeza Pereiro (1995): "Dise{\~n}o de un corpus de lengua de se{\~n}as espa{\~n}ola -- Design of a LSE corpus", XXV Simposium de la Sociedad Espa{\~n}ola de Ling{\"u}{\'i}stica (Zaragoza, 11-14 de diciembre de 1995). \par B{\'a}ez Montero, I. C. {\&} M. C. Cabeza Pereiro (1999): "Spanish Sign Language Project at the University of Vigo" (p{\'o}ster), Gesture Workshop 1999 (Gif-sur-Yvette, Francia, 17-19 de marzo de 1999). \par B{\'a}ez Montero, I. C. {\&} M. C. Cabeza Pereiro (1999): "Elaboraci{\'o}n del corpus de lengua de signos espa{\~n}ola de la Universidad de Vigo -- Development of the Spanish Sign Language corpus of the University of Vigo", Taller de Ling{\"u}{\'i}stica y Psicoling{\"u}{\'i}stica de las lenguas de signos (A Coru{\~n}a, 20-21 de septiembre de 1999). \par At this stage, with renewed energy, we have taken up again our initial aims, crossing the technical, linguistic and sociological obstacles that had hindered our proposal to reach its end. \par In our communication we will present, apart from the difficulties that we have encountered, the new proposals for solving and overcoming them, thus, finally reaching our initial aim: to develop a public Spanish Sign Language corpus that can be consulted online. \par We will go into details with the criteria of versatility and representativity which condition the technical aspects. Technological advances have made possible to adapt the size of the corpus and the criteria for labelling to the interests of the final users. \par The labels for marking the corpus have demanded the revision of the linguistic criteria and the grammatical bases used for describing the language samples that compose the corpus. \par The revision of the sociolinguistic criteria has been caused by the selection of both, the type of discourse (interviews, dialogues, oral speech,...) and the informants chosen for a wider and better representativity in the corpus. \par Finally, we will advance the utilities that we pretend to give the corpus, not only centered in the use of linguistic data for the quantitative and qualitative research of the LSE, but also centered in the use for teaching. The creation of teleteaching platforms allows us to offer the pupil real language samples which complete the process of learning started inside the classroom.} } @inproceedings{debeuzeville:08020:sign-lang:lrec, author = {de Beuzeville, Louise}, title = {Pointing and verb modification: the expression of semantic roles in the {Auslan} Corpus}, pages = {13--16}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08020.html}, abstract = {As part of a larger project investigating the grammatical use of space in Auslan, 62 texts from the Auslan Corpus were annotated and analysed for the spatial modification of verbs to show semantic roles. Data were taken from two groups of native and near-native Auslan signers. Spontaneous narratives were sourced from a sociolinguistic variation corpus collected from 211 participants all over Australia. The second set of texts was elicited from 100 adult native signers of Auslan from the Auslan Corpus Project. Participants retold to a deaf interlocutor a prepared Aesop's fable and a spontaneous personal recount of a memorable event, as well as answering a series of questions on their attitudes to various factors influencing the deaf community (such as genetic testing and cochlear implants). The texts from both corpora were recorded on digital videotape and then annotated using ELAN software. Here we report on 62 texts that have been annotated (approximately 9,000 signs from 50 narrative texts and 9,000 from 10 attitude surveys). Each sign or meaningful gesture was identified, with points being categorised as pronouns or other. These signs were then classified into word class and the nouns and verbs tagged for whether they could be modified spatially. Next, the indicating nouns and verbs were annotated as to whether or not their spatial modification was realised. In this paper, we discuss the use of the ELAN search functions across multiple files in order to identify the proportion of sign types in the texts and the frequency with which indicating verbs are actually modified for space. We then searched all files again to identify all instances where pointing signs occurred directly before or after an indicating verb, in order to calculate whether the collocation of a point (pronoun, other or either) and a non-modified indicating verb was statistically significant. Despite the claim that indicating verbs in signed languages are obligatorily modified (`inflected') with respect to loci in the signing space in order to show person `agreement', we found that these verbs are actually only spatially modified about on third of the time (Johnston et al and de B et al., forthcoming) and this study showed that to be partly as a result of presence of points. The results help determine where and when the spatial modification of indicating verbs is used in natural Auslan texts (and potentially other signed languages). Based on this data, we suggest that 1) the degree of grammaticalization of indicating verbs may not be as great as once thought and 2) the apparent non-obligatory or variable use of spatial modifications may be partly accounted for by the presence of pointing signs---very frequent in signed texts---before or directly after the verb. \par References \par Johnston, T. A., de Beuzeville, L., Schembri, A., {\&} Goswell, D. (2007) On not missing the point: indicating verbs in Auslan. Paper presented at the 10th International Cognitive Linguistics Conference, Krakow, Poland, July 15th -- 20th, 2007 \par de Beuzeville, L., Johnston, T. A., Schembri, A., {\&} Goswell, D. (forthcoming) The use of space with lexical verbs in Auslan.} } @inproceedings{fung:08034:sign-lang:lrec, author = {Fung, Cat H-M and Lam, Scholastica and Mak, Joe and Tang, Gladys}, title = {Establishment of a corpus of {Hong} {Kong} {Sign} {Language} acquisition data: from {ELAN} to {CLAN}}, pages = {17--21}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08034.html}, abstract = {This paper introduces the Hong Kong Sign Language Child Language Corpus currently developed by the Centre for Sign Linguistics and Deaf Studies, the Chinese University of Hong Kong. When completed, the corpus will include both longitudinal and cross-sectional data of deaf children acquiring Hong Kong Sign Language. Our research team has decided to establish a meaning-based transcription system compatible with both the ELAN and CLAN programs in order to facilitate future linguistic analysis. The ELAN program, which allows multiple-tier data entries and synchronization of video data with glosses, is an ideal tool for transcribing and viewing sign language data. The CLAN program, on the other hand, has a wide range of well-developed functions such as auto-tagging and the `kwal' function for data search and they are extremely useful for conducting quantitative analyses. With add-on programs developed by our research team and additional functions in CLAN developed by the CHILDES research team, the transcribed data are transferable from the ELAN format to CLAN format, thus allowing researchers to optimize the use of both programs in conducting different types of linguistic analysis on the acquisition data.} } @inproceedings{fung:08001:sign-lang:lrec, author = {Fung, Cat H-M and Sze, Felix and Lam, Scholastica and Tang, Gladys}, title = {Simultaneity vs. sequentiality: developing a transcription system of {Hong} {Kong} {Sign} {Language} acquisition data}, pages = {22--27}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08001.html}, abstract = {It is a well-known fact that sign languages are characterized with a wide range of simultaneous constructions, e.g. complex polymorphemic constructions, maintenance of list buoys in space while another hand continues signing, overlaying of various types of non-manuals with manual signing, etc. In transcribing these simultaneous constructions, decisions have to be made as to whether they should be given a single gloss or be glossed separately in two different tiers. This presentation discusses the transcription system of Hong Kong Sign Language acquisition data, with particular focus on how simultaneous constructions are analyzed and glossed, and the difficulties we encountered in the transcription process. \par We are currently developing a Hong Kong Sign Language acquisition Corpus (Tang et al.) with transcriptions done with ELAN. One major advantage of ELAN is that it allows us to represent different pieces of linguistic information simultaneously on separate tiers. However, it is not always easy to decide whether two different signs produced by two hands should be glossed as a single sign or be teased apart and glossed separately on two different tiers. For example, in a typical classifier predicate such as `a cup on a table' in example one below, the signs can either be glossed as a single entry `CL-cup-on-table', or marked separately by `CL-cup' and `CL-flat surface' on two different tiers: \par Example (1): `a cup on a table' Left hand: CL-cup \par Right hand: CL-flat-surface \par The advantage of having a single gloss is that it reflects the native intuition that the two classifiers form a single syntactic unit. Yet it fails to reflect the morphological complexity of the construction, leading to a potential underestimation of the morphological development of the deaf child. \par On the other hand, having two separate glosses can clearly show that two classifiers are involved in the construction, reflecting its morphological complexities to some extent. From a theoretical point of view, however, once this method is adopted, the glosses are being used as `analyzable units' to represent separate handshape morphemes. A question that arises logically is, why do we want to represent handshape morphemes separately in the transcription, but not morphemes of other phonological parameters, such as movements and locations? \par Another equally thorny issue is how to gloss classifiers or signs (i.e. list buoy) that are held in space. In example (2), the signer expresses two propositions: `A man stands here' and `a woman shot him with a gun': \par Example (2): \par Left hand: MAN CL-stand --------------------------------------------> Right hand: FEMALE SHOOT-WITH-A-GUN \par In terms of articulation, the classifier for `MAN' is held in space while the second clause is signed. Syntactically, the classifier for MAN becomes the internal argument of the transitive verb SHOOT-WITH-A-GUN in the second clause. In the literature, if a sign is held in space, a broken line is usually used to represent the duration of which the sign is held. If the same method is used in the transcription, however, the fact that the classifier is the internal argument of the second clause cannot be captured. This may potentially lead to an under-estimation of the deaf child's syntactic complexity, if statistics are based on figures generated by the search functions of ELAN. In this presentation, an attempt will be made to provide solutions to the above issues.} } @inproceedings{chetelatpele:08009:sign-lang:lrec, author = {Ch{\'e}telat-Pel{\'e}, Emilie and Braffort, Annelies and V{\'e}ronis, Jean}, title = {Annotation of Non Manual Gestures: Eyebrow movement description}, pages = {28--32}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08009.html}, abstract = {This paper deals with non manual gestures annotation involved in Sign Language (SL) within the context of automatic generation of SL. Movements of the eyes, eyebrows, mouth, cheeks and head involved in SL are defined as non manual gestures or NMG. Many researches in SL emphasize the importance of NMG at different language levels and recognize that NMG are essential for the message comprehension. However these researches can{\'i}t explain and define enough the way that NMG operate. A specific NMG study should allow us to know when and how NMG are involved in meaning transmission and information comprehension, in order to design a formal description usable by automatic generation system. Our purpose is to have an objective and precise description of all NMG involved in French Sign Language (LSF). At present, non manual descriptions do not allow us to deal with and to observe the movement intensity and dynamics. Therefore, we propose a new annotation methodology of NMG. \par We position several 2D points on each frame of the video and export their coordinates x,y. These coordinates are used to obtain precise position of all NMGs frame by frame. Then, we use these data to evaluate the annotation by means of a synthetic face, for numerical analysis (by using curve), and, finally, to obtain numerical definition of each symbol of our set of annotation symbols based on arrows. A first annotation on the LS-COLIN corpus showed that this methodology is an answer to correctly address our purpose: All NMG can be described, with precision. Moreover, the movement dynamics can be analyzed, and each movement phase. All these results must be refined and confirmed by extending the study on the whole corpus. In a second step, our annotation will be used to produce analyses in order to define rules and a formal definition of NGM that will be evaluated in LIMSI{\'i}s automatic LSF generation system.} } @inproceedings{crasborn:08037:sign-lang:lrec, author = {Crasborn, Onno}, title = {Open access to sign language corpora}, pages = {33--38}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08037.html}, abstract = {One of the ongoing developments on internet is the increasing attention for open content: data of all kinds, whether text, images or video, are made publicly available. While there may be restrictions on the type of use that s allowed, selling content and strictly protecting it under copyright laws appears not desirable necessary for some types of content. This development is sometimes characterised as a change from copyright to `copyleft': rather than stating that ``all rights are prohibited'', people are encouraged to use materials for their own benefit. This presentations sketches this development and explores how it can apply to sign language corpora. As a case study, the Corpus NGT project is characterised, which publishes a large systematic collection of sign language data online. A total of 100 signers is being recorded, leading to over 75 hours of material in 2,000 video segments. The wish to publish this material not only for research purposes (cf. the Dutch Science Foundation's funding) stems from its large possible value for various parties in the Netherlands: deaf signers themselves, second language learners of sign language, interpreting students, etc. \par One of the problems in publishing sign language data online is privacy protection. As sign language movies inevitable contain visual information about the identity of the signer, together with the actual content of the language production signers reveal more of themselves than uni-modal speech or text corpora. In the Corpus NGT, we try to protect the privacy of the informants in several ways: we urge people to not reveal too much personal information about themselves or about others in their stories and discussions, we limit the amount of metadata that we publish online (leaving out many of the standard fields from the IMDI metadata standard), and nowhere mention or refer to the name of the signers. \par The way we aim to protect the use of the material is by publishing all materials under a Creative Commons license. Creative Commons is an international organisation that was set up especially as a bridge between national copyright laws and open content material on internet. Of the different types of licenses that are available, we chose to apply the `BY-NC- SA' license. This license states that people may re-use the material provided they refer to the authors, that no commercial use be made, and that (modifications of) the material are distributed under the same conditions. The Creative Commons licenses are attractive because they are made available in various forms: a plain language statement (as in the previous sentence), a formal legal text, and a machine-readable version for use by software. The plain language version is attached to every movie in the Corpus NGT by a short text preceding and following every movie file, thus allowing relatively easy replacement should future changes in policy require so. \par Finally, a few ethical questions are raised in relation to publishing sign language materials as open access data: although the permission for open access publication is requested of the signers in the corpus, to what extent can they foresee the consequences at that point in time? Will future technologies allow easy face recognition on the basis of movies and obliterate the privacy protection measures that have been taken? What will the (normative) effect of publishing signing of a group of 100 signers from a small community be? There is a clear risk in the publication of sign language data without an answer to these questions. The solution taken in the Corpus NGT project is to invest substantial time and energy in publicity within the deaf community, to explain the goal and nature of the corpus and to encourage use by deaf people.} } @inproceedings{crasborn:08022:sign-lang:lrec, author = {Crasborn, Onno and Sloetjes, Han}, title = {Enhanced {ELAN} functionality for sign language corpora}, pages = {39--43}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08022.html}, abstract = {The annotation tool ELAN was enhanced within the Corpus NGT project by a number of new and improved functions. Most of these functions were not specific for working with sign language video data, and can readily be used for other annotation purposes as well. Their direct utility for working with large amounts of annotation files during the development and use of the Corpus NGT project is what unites the various functions. The following functions appeared in a series of releases between versions 2.6 and 3.4:\begin{itemize}\item The `duplicate annotation' function was created to facilitate the glossing of two-handed signs in cases where there are separate tiers for the left and the right hand: copying an annotation to another tier saves annotators quite some time, and prevents misspellings.\item A `multiple file search' was implemented: structured searches combining search criteria on different tiers can be carried out in a subset of files that can be created by the user.\item The segmentation function was further developed so that annotations with a fixed, user definable duration can be created by a single key stroke while the media files are playing. The key stroke can either mark the beginning of an annotation or the end.\item A function has been added to flexibly generate annotation content based on a user definable prefix and an index number.\item A panel can be displayed that lists basic statistics for all tiers in an annotation document: the number of annotations, the minimum, maximum, average, median and total annotation duration per tier. This helps the user getting a better grip on the content in an annotation document and can be helpful in data analysis.\item The annotation density viewer can now also be set to only show the distribution of annotations of a single, selectable tier. The label of a tier in the timeline viewer can optionally show the current number of annotations on that tier.\item The property `annotator' has been added in the specification of tiers, allowing groups of researchers to separate which tier has been filled by whom.\item Export a list of unique annotation values or a list of unique words from multiple annotation documents.\item Easy, interactive hiding and showing of any of the associated video files, without having to remove the media file association altogether.\end{itemize} \par In addition, a large number of user interface improvements have been implemented, including the following:\begin{itemize}\item Improved, more intuitive layout of the main menu bar\item Additional keyboard shortcuts; the list of shortcuts can be printed\item A recent files list has been added\item Easy keyboard navigation through the opened documents/windows\item A subtle change in the background of the timeline viewer, facilitating the perception of the distinction between the different tiers\item With the use of a new preferences system in version 3, users can now set the colour of tier labels in the timeline viewer, allowing the visual grouping of related tiers in documents containing many tiers.\end{itemize} \par Although enhanced search functionalities and templates facilitate working with multiple ELAN documents, it is not yet possible to `manage' a set of ELAN files systematically in any way. Perl scripts were developed in order to add tiers and linguistic types to a set of documents, to change annotation values in multiple documents, and to generate ELAN and preferences files on the basis of a set of media files and existent annotation and preferences files. \par Future collaboration between the ELAN developers at the Max Planck Institute for Psycholinguistics and the sign language researchers at Radboud University will be targeted at enhancing search facilities and facilitating team work between researchers using large language corpora containing ELAN documents.} } @inproceedings{crasborn:08003:sign-lang:lrec, author = {Crasborn, Onno and Zwitserlood, Inge}, title = {The {Corpus} {NGT}: an online corpus for professionals and laymen}, pages = {44--49}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08003.html}, abstract = {The Corpus NGT is an ambitious effort to record and archive video data from Sign Language of the Netherlands (NGT), guaranteeing online access and long-term availability. In this presentation, we share our experiences in building this corpus, viz. preparing for comparable data, both elicited and (semi)spontaneous, the recording set-up and procedure, processing of the data, annotation, metadata, licenses and publishing. \par Initially aiming to record 24 native signers using two variants of NGT, and providing annotations of a large amount of the data, the plan changed into recording many more signers (100) using all five reported variants of NGT. This much larger collection of data ensures a good sample of the current state of the language, and, since participants are from various ages, we can also include its older stages (facilitating the study of language change). The consequence is that there is less time for making annotations. However, it will be easier to add annotations later than to make new recordings that are comparable in every respect to the initial recordings. \par The project strives towards a completely open access policy: not only the video data and annotations will be available to everyone, but also the workflows and manuals for tools that have been used. Use and reuse of the data are protected by Creative Commons licenses. For now, the corpus will be published by the Max Planck Institute for Psycholinguistics, as part of their growing set of language corpora. We follow their IMDI standard for creating metadata descriptions and corpus structuring. The extension of their annotation tool ELAN as well as the integration of ELAN and IMDI (the data and metadata domains) formed a substantial part of the project. \par The Corpus NGT project is funded by the Dutch Science Foundation to facilitate linguistic research. However, since there is a dire need for NGT data among several groups of people, we now are happy to include everyone in our target audience. Other interested scientists may be psychologists, educators, and those involved in constructing (sign) dictionaries. Deaf and hearing professionals in deaf schools and in the Deaf community are interested, including teachers of NGT, developers of teaching materials, and interpreters. Many hearing learners of NGT will benefit from open access to a large set of data in their target language. Deaf people themselves may be interested in the discussion on deaf issues that forms part of every recording session. \par Participants were recorded in pairs. They performed several language tasks (producing narratives, prompted discussions, but also non-elicited signing), resulting in ±1.5 hours of useable signed data per pair. Both upper body and a top view were recorded of each signer. In combination, these recordings approximate a three-dimensional view of the signing. For extra information of the facial expressions, MPEG-1 movies showing only the face are extracted from the recordings of the body (shot in full HD resolution). \par Due to time and budget limitations, it was only possible to make crude gloss annotations in ELAN of a small subset of the data. In order to make as much of the data set accessible to a large audience, a voice-over done by interpreters is provided with most of the data.} } @inproceedings{dreuw:08038:sign-lang:lrec, author = {Dreuw, Philippe and Ney, Hermann}, title = {Towards Automatic Sign Language Annotation for the {ELAN} Tool}, pages = {50--53}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08038.html}, abstract = {A new interface to the ELAN annotation software that can handle automatically generated annotations by a sign language recognition and translation framework is described. For evaluation and benchmarking of automatic sign language recognition, large corpora with rich annotation are needed. Such databases have generally only small vocabularies and are created for linguistic purposes, because the annotation process of sign language videos is time consuming and requires expert knowledge of bilingual speakers (signers). The proposed framework provides easy access to the output of an automatic sign language recognition and translation framework. Furthermore, new annotations and metadata information can be added and imported into the ELAN annotation software. Preliminary results show that the performance of a statistical machine translation improves using automatically generated annotations. \par Automatic sign language recognition is a problem that is being solved by many research institutes in the world. Up to now there is a deficiency of corpora with good properties such as high resolution and frame rate, several views of the scene, detailed annotation etc. In this paper we take a closer look at the annotation of available data.} } @inproceedings{dudis:08036:sign-lang:lrec, author = {Dudis, Paul and Mulrooney, Kristin and Langdon, Clifton and Whitworth, Cecily}, title = {Annotating Real-Space Depiction}, pages = {54--57}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08036.html}, abstract = {``Shifted referential space'' (SRS) and ``fixed referential space'' (FRS) (Morgan 2005) are two major types of referential space known to signed language researchers (see Perniss 2007 for a discussion of alternative labels used in the literature). An example of SRS has thesigner's body representing an event participant. An example of FRS involves the use of ``classifier predicates'' to demonstrate spatial relationships of entities within a situation being described. A number of challenges in signed language text transcriptions identified in Morgan (2005) pertains to the use of SRS and FRS. As suggested in this poster presentation, a step towards resolving some of these challenges involves greater explicitness in the descriptionof the conceptual make-up of SRS and FRS. Such explicitness is possible when more than just the signer's body, hands, and space are considered in the analysis. Dudis (2007) identifies the following as components within Real- Space (Liddell 1995) that are used to depict events, settings and objects: the setting/empty physical space, the signer's vantage point, the subject of conception (or, the self), temporal progression, and the body and its partitionable zones. We considered these components in a project designed to assist videocoders to identify and annotate types of depiction in signed language texts. Our preliminary finding is that if we also consider the conceptual compression of space---which results in a diagrammatic space (Emmorey and Falgier 1999)---there are approximately fourteen types of depiction, excluding the more abstract ones, e.g. tokens (Liddell 1995). \par Included in this poster presentation is a prototype of a flowchart to be used by video coders as part of depiction identification procedures. This flowchart is intended to reduce the effort of identifying depictions by creating binary (yes or no) decisions for each step of the flowchart. The research team is currently using ELAN (EUDICO Linguistic Annotator, www.lat-mpi.eu/tools/elan/) to code the depictions focusing on the relationship of genre and depiction type by looking at the depictions' length, frequency, and place of occurrence in 4 different genres: narrative of personal experience, academic, poetry, conversation. We also have been mindful that a good transcription system should be accessible in an electronic form and be searchable (Morgan 2005). In tiered transcription systems like ELAN the depiction annotation can simply be a tier of its own when it is not the emphasis of the research, or it can occupy several tiers when it is the forefront. In linear ASCII- style transcriptions the annotation can mark the type and beginning then end of the depiction. Our poster does not bring a complete bank of suggested annotation symbols, but rather the idea that greater explicitness as to the type of depiction in question may be beneficial to corpus work.} } @inproceedings{efthimiou:08030:sign-lang:lrec, author = {Efthimiou, Eleni and Fotinea, Stavroula-Evita}, title = {Annotation and Maintenance of the {Greek} {Sign} {Language} Corpus ({GSLC})}, pages = {58--63}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08030.html}, abstract = {This paper presents the design and development of a representative language corpus for the Greek Sign Language (GSL). Focus is put on the annotation methodology adopted to provide for linguistic information and annotated corpus exploitation for the extraction of a linguistic model intended to support HCI applications based on sign recognition. \par The existence of an annotated corpus is a prerequisite for the creation of linguistic resources and for the development of NLP applications for any natural language articulated either orally or through signing. In the case of a sign language corpus, annotation performed on video sequences, is intended to support exploitation of linguistic information conveyed through various combinations of spatial-temporal parameters around the signer's body. \par The Greek Sign Language Corpus (GSLC) is been developed in the framework of the national project DIANOEMA (GSRT, M3.3, id 35) that aims at optical analysis and recognition of both static and dynamic signs, incorporating a GSL linguistic model in controlling robot motion. Since no previous GSL corpus is available to meet the requirements of multipurpose use in an HCI environment, the design of GSLC has taken into account annotation requirements as well as linguistic adequacy controls to ensure both corpus-based linguistic analysis and corpus re-usability. Linguistic analysis is a sufficient component for the development of NLP tools that, in the case of signed languages, support deaf accessibility to IT content and services. To effectively support this kind of language intensive operations, linguistic analysis has to derive from safe language data and also provide for an amount of linguistic phenomena, which allow for an adequate description of the language structure. In this context, safe data are defined as data commonly accepted by a specific language community. The design of GSLC content has made a distinction between three parts on the basis of the articulation units to be considered in respect to both linguistic analysis and the sign recognition process. \par The first part comprises a list of lemmata which are representative of the use of handshapes as a primary sign formation component. This part of the corpus is developed on the basis of measurements of handshape frequency of use in sign morpheme formation but it has also taken into account the complete set of sign formation parameters. In this sense, in order to provide data for all sign articulation features of GSL, the corpus also includes characteristic lemmata with respect to all manual and non-manual features of the language. The second part of GSLC is composed of sets of controlled utterances, which form paradigms capable to expose the mechanisms GSL uses to expresses specific core grammar phenomena. The grammar coverage that corresponds to this part of the corpus is representative enough to allow for a formal description of the main structural-semantic mechanisms of the language. Finally, the third part of GSLC contains free narration sequences, which are intended to provide data of spontaneous language production and be used for machine learning purposes as regards sign recognition. With respect to data collection, all parts of the corpus have been performed by native signers under controlled conditions that guarantee absence of language interference from the part of the spoken language of the signers' environment. Finally, quality control mechanisms have been applied to ensure data integrity. \par In the framework of the current research target, annotation on the GSLC involves, on the one hand, descriptions of the phonological structure of morphemes and, on the other hand, sentence level markers. Sign phonology involves manual and non-manual features of sign formation. For the description of the phonological composition of sign morphemes the HamNoSys coding set is being used along with GSL specific feature coding. Sentence level annotation, except for sentence boundaries, involves phrase boundary marking and grammar information marking related to multi-layer indicators, as is the case of e.g. topicalisation, nominal phrase formation, temporal indicators and sentential negation. Sentence level annotation makes use of the ELAN annotator. Annotation integrity is subject to quality controls that involve both peer and external review by expert annotators. \par The GSLC current implementation has foreseen extensibility on all content levels as well as on annotation features, thus, allowing for corpus re-usability in GSL research and HCI applications beyond the scope of a specific research project. \par Indicative bibliography \par Bowden, R., Windridge, D., Kadir, T., Zisserman, A. {\&} Brady, M. (2004). «A Linguistic Feature Vector for the Visual Interpretation of Sign Language», In Tomas Pajdla, Jiri Matas (Eds), Proc. 8th European Conference on Computer Vision, ECCV04. LNCS3022, Springer-Verlag, Volume 1, pp391- 401. \par Bellugi, U. {\&} Fischer, S. (1972). «A comparison of Sign language and spoken language: rate and grammatical mechanisms», Cognition: International Journal of Cognitive Psychology, 1, 173-200. \par Efthimiou, E., Sapountzaki, G., Karpouzis, C. {\&} Fotinea, S-E. (2004). «Developing an e-Learning platform for the Greek Sign Language». Lecture Notes in Computer Science 3118: 1107-1113. Springer. \par Efthimiou, E., Fotinea, S-E. {\&} Sapountzaki, G. (2006). «Processing linguistic data for GSL structure representation»,Proc. of the Workshop on the Representation and Processing of Sign Languages: Lexicographic matters and didactic scenarios, Satellite Workshop to LREC-2006 Conference, May 28, pp.49-54. \par ELAN annotator, Max Planck Institute for Psycholinguistics, available at: http://www.mpi.nl/tools/elan.html \par Fotinea, S-E., Efthimiou, E., Karpouzis, K. {\&} Caridakis, G. (2005). ``Dynamic GSL synthesis to support access to e-content'', Proc. of the 3rd International Conference on Universal Access in Human-Computer Interaction (UAHCI 2005), 22-27 July 2005, Las Vegas, Nevada, USA. \par HamNoSys Sign Language Notation System: www.sign-lang.uni-hamburg.de/projects/HamNoSys.html \par Karpouzis, K. Caridakis, G., Fotinea, S-E. {\&} Efthimiou, E. (2005). ``Educational Resources and Implementation of a Greek Sign Language Synthesis Architecture'', Computers and Education International Journal, Elsevier, in print, electronically available since Sept 05. \par Kraiss, K.-F. (Ed.), (2006). Advanced Man-Machine Interaction - Fundamentals and Implementation. Series: Signals and Communication Technology, Springer. \par Stokoe, W. 1978. Sign Language Structure (revised ed.). Silver Spring, MD: Linstok.} } @inproceedings{hanke:08011:sign-lang:lrec, author = {Hanke, Thomas and Storz, Jakob}, title = {{iLex} -- A Database Tool for Integrating Sign Language Corpus Linguistics and Sign Language Lexicography}, pages = {64--67}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08011.html}, abstract = {This poster presents iLex, a software tool targeted at both corpus linguistics and lexicography. It is now a shared belief in the LR community that lexicographic work on any language should be based on a corpus. Conversely, lemmatisation of a sign language corpus requires a lexicon to be built up in parallel. \par For languages with a written form and orthography, lemmatisation is a more or less straight-forward process. For sign languages, however, type-token matching is a major task by itself. Glossing or form- based transcription, e.g. with HamNoSys, may be sufficient for small single-transcriber projects. Consistency, however, cannot be guaranteed over multiple transcribers, large quantities, or longer periods of time. \par iLex is therefore designed as a relational database linking tokens with their types. That means that the transcription process does not consist of assigning text tags to time intervals of the source video, but of tagging intervals with a reference to a type. The database then allows the user to review all tokens of a type at any point of time in order to verify that the intended type-token pair really fits with the type's definition and extension. Revisions of earlier decisions in the light of new data are as easy as dragging instances from one type to the other. Beyond the support in the initial type-token matching, iLex gives its users views onto the transcribed data orthogonal to the transcription itself, and thereby helps to improve transcription quality. With its ability to support users working on different projects in one database, iLex allows synergies between projects as each project immediately profits from data entered by others. The cost for these benefits is the necessity of a solid infrastructure: A database server needs to be installed, and ideally every user should have access to all videos, often requiring specialised video servers. For larger corpus projects, however, this should be taken for granted anyway. For data exchange with other research groups, iLex supports a number of file formats, such as ELAN, SignStream, and syncWRITER for transcription data and IMDI for metadata. While exporting data from iLex into these formats as well as a couple of presentation formats such as HTML with thumbnails is done with a simple menu command, importing data from other sources requires some additional steps to be done by the researcher. As other data formats consist of text tags only, some matching operations are necessary to convert from text to tokens. The newest release of iLex supports the user in this procedure: By learning a mapping from imported glosses to iLex types from user actions, it can partially automate future imports from the same source. In addition to data exchange with other transcription tools and export to presentation formats, iLex integrates with a number of tools for rapid production of sign language teaching materials and for virtual signing by means of avatars. \par On the lexicography side, iLex can host all the data necessary for the production of dictionaries. With its scripting language support, iLex is able to almost completely automate the production of a variety of formats including print, DVD, online websites for computers, and online websites for iPods/iPhones.} } @inproceedings{herrmann:08015:sign-lang:lrec, author = {Herrmann, Annika}, title = {Sign language corpora and the problems with {ELAN} and the {ECHO} annotation conventions}, pages = {68--73}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08015.html}, abstract = {Large corpus projects require logistic, technical and personal expertise and most importantly a conventionalized annotation system. In addition, relatively small projects with a definite set of data can also be an invaluable contribution to linguistic sign language research and therefore should use the same technical methods and annotation conventions for comparative reasons. The poster will present the process of building a corpus that is needed for a cross-linguistic study currently undertaken and focuses on the problems that arise with regard to annotation. The respective solutions shall be suggestions towards a unified convention. \par In this project, elicited data from three European sign languages and altogether 20 informants provide a set of approx. 900 sentences and short dialogues. Metadata information about participants and the recording situation will be edited in the IMDI metadata set. ELAN provides the most adequate annotation system for my purposes as the main interest of the study lies in the use of nonmanuals. The tool is widely used for sign language annotation and I try to guarantee for comparability by mainly adopting the ECHO annotation system with a few necessary adaptations. \par Problems listed below include repeatedly asked questions that are still not defined clearly yet: \par a) How are the on- and offsets of signs determined? Shall we annotate the separate signs or the signing stream integrating the transition period? \par b) How should pointing signs or constructions with many meaning components be transcribed? \par c) Despite more or less clear definitions of what each tier should be used for, the GLOSS-tier is sometimes intertwined with external information not fitting the tier. How can these problems be avoided? \par d) What kinds of disadvantages occur, if the eye gaze and eye blink annotations are not accurate? \par Possible Solutions: \par a) Even though the on- and offsets of signs can be defined more precisely than for words, the sign syllable not always has clear boundaries. Signing should be annotated as a streaming process that is interrupted when there is a hold or a significant pause. The transition from one sign to the other is often clearly visible through handshape change, which seems to be the more adequate marker for annotation. (The only problem left being sign duration, which cannot entirely be solved by the vague separate sign annotation either.) \par b) Proposal for a more detailed distinction of pointing signs without being theoretical (at least IX-1 for signer, IX-dual (excl., incl.) e.g.) and poly-meaning constructions (e.g. BE-LOCATED-CL:vehicle instead of (p-)vehicle-be-located; BLEAK instead of (p-)bleaking sheep when SHEEP is already introduced, decision between HOLD-CL:potato and HOLD-CL:round object). \par c) The GLOSS tier should only be used for manual signs or gestures, nonmanuals should not be included (*WALK- PURPOSEFUL). An additional tier is useful: other NMFs/look/other facial expressions \par d) Continuous eye gaze and eye aperture annotation is necessary to exactly determine eye gaze change with or without an eye blink and the duration and timing of blinks. This can especially be relevant for prosodic analysis.} } @inproceedings{hemann:08024:sign-lang:lrec, author = {He{\ss}mann, Jens and Vaupel, Meike}, title = {Building up Digital Video Resources for Sign Language Interpreter Training}, pages = {74--77}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08024.html}, abstract = {Sign language interpreter training has been offered at the universities of applied sciences in Magdeburg and Zwickau since 1997 and 1998, respectively. Both training programs are set in the institutional context of East German universities that experienced a major reorganization after the unification of Germany. The training programs share an applied perspective in research and teaching as well as many of the features typical for small scale academic ventures in a developing field. Thus, provision of teaching materials and, more particularly, sign language video resources, adequate in content, format and technical quality, has been a constant concern. Of necessity, a hands-on approach had to be chosen for the last ten years, and both programs have amassed a diversity of analogue and digital video films. In most cases, the only way of accessing this material consists in picking the brains of those colleagues who may have worked with some video clip or exercise suitable for one's own didactic or research purposes. \par As it happens, Magdeburg as well as Zwickau have installed the same type of digital training facilities (`video lab') in 2007. These video labs consist of individual workstations linked to a central video server that hosts all the resources in a unified digital format. For both institutions, a major challenge consists in organizing a process that will transform and complement existing sign language materials so as to create an accessible library of video resources for research and training purposes. Our presentation will report on our joint efforts to do the first steps in this direction. The following aspects will be discussed:\begin{itemize}\item Legal and ethical issues: Up to now, questions of ownership and property rights have often been dealt with somewhat casually. Building up a digital library of video resources implies that such questions have been formally clarified. However, just what the conditions for using video materials gathered informally, passed on from one colleague to the next or published on the internet are, may be hard to decide.\item Administrative and technical prerequisites: In order to create a solid basis for the desired cooperation and be able to access university funds, the two universities concerned will enter into formal agreements on the mutual use of video resources. This in turn, demands that there are clearly defined ways of synchronizing, complementing and accessing the respective collections of resources.\item Criteria for annotating and archiving video resources: While the process of digitizing and storing existing video materials can be dealt with somewhat mechanically, the development of systematic ways of annotating and organising sign language materials is crucial in order to make digital resources accessible. Clearly, this is an area where progress has been made in recent years, e.g. in the context of the ECHO project (`European Cultural Heritage Online,' cf. http://www.let.ru.nl/sign-lang/echo/index.html). We will add to this discussion by considering the more specific demands of sign language interpreter training and research.\end{itemize}} } @inproceedings{hruz:08013:sign-lang:lrec, author = {Hr{\'u}z, Marek and Campr, Pavel and {\v Z}elezn{\'y}, Milo{\v s}}, title = {Semi-automatic Annotation of Sign Language Corpora}, pages = {78--81}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08013.html}, abstract = {The first step of automatic sign language recognition is feature extraction. It has been shown which features are sufficient for a successful classification of a sign. It is the hand shape, orientation of the hand in space, trajectory of the hands and the non-manual component of the speech (facial expression, articulation). Usually the efficiency of the feature extracting algorithm is evaluated by the rate of recognition of the whole system. This approach can be confusing since the researcher cannot be always sure which part of the system is failing. However if the corpora would be available with a detailed annotation of these features the evaluation would be more precise. A manual creation of the annotation data can be very time consuming. We propose a semi-automatic tool for annotating trajectory of head and hands and the shape of the hands. \par For the purpose of extracting the trajectory of hands a tracker is developed. In our case the tracker is based on similarity of the scalar description of objects. We describe the objects by seven Hu moments of the contour, a gray scale image (template), position, velocity, perimeter of the contour, area of the bounding box and area of the contour. For every new frame all objects in the image are detected and filtered. Every tracker computes the similarity of the tracked object and the evaluated object. As long as the tracker's certainty is above a threshold it is considered as ground truth. At this point all available data are collected from the object and saved as annotation. If the level of uncertainty is high, the user is asked to verify the tracking. \par If a perfect tracker was available all the annotation could be created automatically. But the trackers usually fail when an occlusion of objects occurs. Because of this problem the system must be able to detect occlusions of objects and have the user verify the resulting tracking. In our system we assume that the bounding box of an overlapped object becomes relatively bigger in the first frame of occlusion and relatively smaller in the first frame after occlusion. We consider the area of the bounding box as a feature which determines the occlusion. \par Up to now the annotation through tracker allows us to semi-automatically obtain the trajectory of head and hands and the shape of the hands. In the future we will extend the system to be able to determine the orientation of hands and combine it with a lip-reading system which we have ready for use. The obtained parameters can be then used as ground truth data for evaluation of feature extracting algorithm.} } @inproceedings{johnston:08031:sign-lang:lrec, author = {Johnston, Trevor}, title = {Corpus linguistics and signed languages: no lemmata, no corpus}, pages = {82--87}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08031.html}, abstract = {A fundamental problem in the creation of signed language corpora is lemmatisation. Lemmatisation---the classification or identification of related word forms under a single label or lemma (the equivalent of headwords or headsigns in a dictionary)---is central to the process of corpus creation. The reason is that signed language corpora---as with all modern linguistic corpora---need to be machine-readable and this means that sign annotations should not only be informed by linguistic theory but also that tags appended to these annotations should be used consistently and systematically. In addition, a corpus must also be well documented (i.e., with accurate and relevant metadata) and representative of the language community (i.e., of relevant registers and sociolinguistic). All this requires dedicated technology (e.g., ELAN), standards and protocols (e.g., IMDI metadata descriptors), and transparent and agreed grammatical tags (e.g., grammatical class labels). However, it also requires the identification of lemmata and this presupposes the unique identification of sign forms. In other words, a successful corpus project presupposes the availability of a reference dictionary or lexical database to facilitate lemma identification and consistency in lemmatisation. Without lemmatisation a collection of recordings with various related appended annotation files will not be able to be used as a true linguistic corpus as the counting, sorting, tagging. etc. of types and tokens is rendered virtually impossible. This presentation draws on the Australian experience of corpus creation to show how a dictionary in the form of a computerized lexical database needs to be created and integrated into any signed language corpus project. Plans for the creation of new signed language corpora will be seriously flawed if they do not take this into account.} } @inproceedings{kanis:08012:sign-lang:lrec, author = {Kanis, Jakub and Kr{\v n}oul, Zden{\v e}k}, title = {Interactive {HamNoSys} Notation Editor for Signed Speech Annotation}, pages = {88--93}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08012.html}, abstract = {The goal of sign language synthesis is to create an avatar which uses sign languge as main communication form. In order to emulate human behaviour during signing the avatar has to express manual components (hand position, hand shape) and non-manual components (face expression, lip articulation) of the performed signs. The task of sign language synthesis is implemented in several steps. Since the sign language has different grammar than the spoken language, the source sentence has to be translated into corresponding sequence of isolated signs. Those signs are synthesized in sequence and create output sentence in sign language. Non-manual components are synthesized by already developed Czech talking head which is able to articulate words and sentences in Czech language. Face expressions can be manually set. The synthesis process of manual movements is based on HamNoSys 3.0 notation. This notation is used for deterministic and suitable processing of the sign speech. The methodology of the notation allows precise and also extensible expression of the sign description. \par Firstly, our synthesis system automatically carries out the syntactic analysis of symbolic string (in HamNoSys notation) and generates a tree structure. The tree structure is suitable for conversion of the symbols to tra jectories with application parse rules. The parsing rules were manually formed to cover all HamNoSys notation variants. There are 39 rule actions forming complete animation tra jectories. For this purpose 138 HamNoSys symbols are currently adopted. The processing of the tree is carried out by several tree walks whilst the size of the tree is reduced. The final animation tra jectories in the root node are transformed by an inverse kinematics technique to control the joints of avatar animation model. The analysis of HamNoSys symbols allows us to animate hands and the upper half-body. Thus a single sign is encoded by corresponding sequence of HamNoSys symbols. \par We have developed an interactive tool which purpose is to extend our database of signs. The main application window contains list of symbols which can be clicked and added into the sequence. This sequence can be immediately converted into the movement of the avatar which is shown in the second window. This allows fast production of symbol sequences for new signs and easy modification of existing signs since the changes are directly visible. In addition it allows people who have no high experince with HamNoSys to learn it faster. At present our database contains about 300 signs which are encoded as sequeces of HamNoSys symbols. This first database is targeted to the information system for train connections. Further expansion of the database will add new areas where the avatar can be used.} } @inproceedings{konig:08017:sign-lang:lrec, author = {K{\"o}nig, Lutz and K{\"o}nig, Susanne and Konrad, Reiner and Langer, Gabriele}, title = {Corpus-based Sign Dictionaries of Technical Terms -- Dictionary Projects at the {IDGS} in {Hamburg}}, pages = {94--100}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08017.html}, abstract = {At the Institute of German Sign Language (IDGS), six dictionary projects in such diverse technical fields as computer technology, psychology, joinery, domestic science, social work as well as health and nursing care have been carried out. A seventh project on landscaping and horticulture is in progress. Six of the seven dictionaries are based on a corpus collected from deaf experts in the respective fields. Elicitation methods, such as interviews and picture prompts, corpus design as well as annotation, transcription, sign analysis and dictionary production have been continually developed and refined over the years. Many procedures rely heavily on the use of a relational database system iLex (see other presentation). \par The presentation provides an overview of the projects, procedures and products with special attention given to the issues of corpus-building for and corpus-relatedness of the dictionaries at most stages of analysis and production. We focus on the corpus-based selection process which translations to include in the dictionary and on the analysis of single signs. \par From 1998 on, the dictionaries do not only provide translations of technical terms into DGS but also include a special section that lists single signs used in these translations in separate entries. The structure of these entries is similar to what you would expect from a general sign language dictionary. Information including lexical status, meaning, use of space, iconic value and cross references to similar signs is given for each sign. However, due to the limited size of each of these corpora and the elicitation methods used, not all information can be drawn from or validated by the corpus. \par Within the scope of the projects, assumptions and practical decisions have been made to deal with lexicological and lexicographical issues. These include the identification of lexemes, the degree of lexicalisation, i.e. the lexical status of signs and their meanings, the role of mouthings, and the relations between signs (polysemes vs. homonyms, modifications and variants). One important criterion for these decisions is the iconic value of signs. \par The lexicographic solutions applied to specialised sign language dictionaries also provide a solid basis for general sign lexicography as well as corpus annotation and lexical analysis.} } @inproceedings{koskela:08002:sign-lang:lrec, author = {Koskela, Markus and Laaksonen, Jorma and Jantunen, Tommi and Takkinen, Ritva and Rain{\`o}, P{\"a}ivi and Raike, Antti}, title = {Content-Based Video Analysis and Access for {Finnish} {Sign} {Language} -- A Multidisciplinary Research Project}, pages = {101--104}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08002.html}, abstract = {In this research project, computer vision techniques for recognition and analysis of gestures and facial expressions from video will be developed and the techniques will be applied for processing of sign language. This is a collaborative project between four partners: Helsinki University of Technology, University of Art and Design, University of Jyv{\"a}skyl{\"a}, and the Finnish Association of the Deaf. It has several objectives of which four are presented in more detail in this poster. \par The first objective is to develop novel methods for content-based processing and analysis of sign language video recorded using a single camera. The PicSOM retrieval system framework developed by the Helsinki University of Technology regarding content-based analysis of multimedia data will be adapted to continuous signing to facilitate automatic and semi-automatic analysis of sign language videos. \par The second objective of the project is to develop a computer system which can both (i) automatically indicate meaningful signs and other gesture-like sequences from a video signal which contains natural sign language data, and (ii) disregard parts of the signal which do not count as such sequences. In other words, the goal is to develop an automatized mechanism which can identify sign and gesture boundaries and indicate, from the video, the sequences that correspond to signs and gestures. The system is not expected to be able to tell the meanings of these sequences. \par An automatic segmentation of recorded continuous-signing sign language is an important first step in the automatic processing of sign language videos and online applications. It is our hypothesis that the temporal boundaries of different sign gestures can be detected and signs and non-signs (intersign transitions, other movements) can be classified using a combination of a hand motion detector, still image multimodal analysis, facial expression analysis and and other non- manual signal recognition. The PicSOM system inherently supports such fusion of different features. \par The third objective is linked to generating an example-based corpus for FinSL. There exist increasing amounts of recorded video data of the language, but almost no means for utilizing it efficiently due to missing indexing and lack of methods for content-based access. The studied methods could facilitate a leap forward in founding the corpus. \par The fourth objective is a feasibility study for the implementation of mobile video access to sign language dictionaries and corpora. Currently an existing dictionary can be searched by giving a rough description of the location, motion and handform of the sign. The automatic content-based analysis methods could be applied to online mobile phone videos, thus enabling sign language access to dictionaries and corpora.} } @inproceedings{krammer:08029:sign-lang:lrec, author = {Krammer, Klaudia and Bergmeister, Elisabeth and Bornholdt, Silke and Dotter, Franz and Hausch, Christian and Hilzensauer, Marlene and Pirker, Anita and Skant, Andrea and Unterberger, Natalie}, title = {The {Klagenfurt} lexicon database for sign languages as a web application: A free sign language database for international use}, pages = {105--111}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08029.html}, abstract = {Klagenfurt University has created a database which is described in Sign Language {\&} Linguistics 4 (2001), 191-201. The objective of turning it into a web application was to offer our database for sign languages and users all over the world. In accordance with the self-conception of the Internet community and the rules of linguistic ethics, this is a basic service for sign language communities: the database can be used for free for non-commercial deaf and scientific issues. \par As for the procedure: In order to add a sign language to the database, you need to provide a legitimation from the respective deaf organisation (i.e. of those people who use the sign language in question regionally or nationally), then you will be authorised to enter the data for this sign language into the database. By entering data you open them for communities of deaf people, scientists, and learners. \par The data of the sign languages entered in the database will be stored on a Klagenfurt server. There is no limitation on calling up sign language data (searching for a certain sign or parameter value(s) etc.). For downloading videos, the users have to disclose their identity. \par Main characteristics of the database \par The database is designed in a way that everything which should appear in any monolingual or bilingual dictionary can be entered. All descriptive categories are as closely related to phenomena as possible. The analysis of the categories does not have to follow a strictly linear procedure or any assumed phonological or grammatical hierarchy. Additionally it offers:\begin{itemize}\item Openness of the sets of categories and their values (the users can add new categories or values to the database at their discretion). They can also translate the English terms of the description language into any other language which uses an alphabet.\item Quick production of entries: In order to enable the users to enter signs as fast as possible, we provide the possibility of a "minimum entry": it is sufficient to enter only one item, e.g. a single meaning, and then to store the sign video. The entries can then be amended later on.\end{itemize} \par Fields of data types within the database\item Type of sign (e.g. one-handed or two-handed symmetrical/asymmetrical; hand shape, location, orientation, type of contact, type of movement, intensity, etc.)\item Non-manual component: facial gestures, mouth gestures, body orientation, eye gaze, etc.\item Semantics: translation equivalents for a bilingual dictionary or explanation in the respective sign language for a monolingual dictionary); connotations or sign etymologies can also be added.\item Pragmatics: use, collocations, or idioms can be documented with video examples.\item Text/context examples\item Morphosyntax: categories of parts of speech, coding properties (e.g. morphological changes or position in a sentence or phrase) and syntactic functions\item Word field(s).} } @inproceedings{leeson:08004:sign-lang:lrec, author = {Leeson, Lorraine and Nolan, Brian}, title = {Digital Deployment of the Signs of {Ireland} Corpus in Elearning}, pages = {112--122}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08004.html}, abstract = {The Signs of Ireland corpus is part of the School of Linguistic, Speech and Communication Sciences' ``Languages of Ireland'' project. The first of its kind in Ireland, it comprises 40 male and female signers from across the Republic of Ireland, aged 18-65+, all of whom were educated in a school for the Deaf. The object was to create a snapshot of how ISL is used by `real' signers across geographic, gendered and generational boundaries, all of which have been indicated as sociolinguistically relevant for ISL (cf. the work of Le Master; also see Leeson and Grehan 2004, Leonard 2005, Leeson et al. 2006). With the aim of maximising the potential of cross-linguistic comparability, we mirrored aspects of data collection on other corpora collected to date. Thus, we include the Volterra et al. picture elicitation task (1984), ``The Frog Story'', and also asked informants to tell a self-selected story from their own life. To date, all of the self-selected stories have been annotated using ELAN. \par Two institutions (CDS, TCD and ITB) have partnered to create a unique elearning environment based on MOODLE as the learning management system. This delivers third level signed language programmes to a student constituency in a way that resolves problems of time, geography and access, maximizing multi-functional uses of the corpus across programmes. Students can take courseware synchronously and asynchronously. We have now built a considerable digital asset and plan to re-architect our framework to avail of current best practice in digital repositories and digital learning objects vis-{\`a}-vis Irish Sign Language. \par This paper outlines the establishment and annotation of the corpus, and the success of the corpus to date in supporting curricula and research. This paper focuses on moving the corpus forward as an asset to develop digital teaching objects. This paper outlines the challenges inherent in this process, and outlines our plans and our progress to date in meeting these objectives. Specific issues include:\begin{itemize}\item Decisions regarding annotation\item Establishing mark-up standards\item Use of the Signs of Ireland corpus in elearning/ blended learning contexts\item Leveraging a corpus within digital learning objects\item Architecture of a digital repository to support sign language learning\item Tagging of learning objects versus language objects\item Issues of assessment in an elearning context\end{itemize} \par References \par Lorraine Leeson, John Saeed, Cormac Leonard, Alison Macduff and Deirdre Byrne-Dunne 2006: Moving Heads and Moving Hands: Developing a Digital Corpus of Irish Sign Language: The `Signs of Ireland' Corpus Development Project. Paper presented at the IT{\&}T conference, Carlow, 2006. \par Leeson, L. and C. Grehan 2004: To the Lexicon and Beyond: The Effect of Gender on Variation in Irish Sign Language. In M. Van Herreweghe and M. Vermeerbergen (eds.): To The Lexicon and Beyond: The Sociolinguistics of European Sign Languages. Gallaudet University Press. 39-73. \par Le Master, B. 1990: The Maintenance and Loss of Female and Male Signs in the Dublin Deaf Community. PhD Dissertation. Los Angeles: University of California. \par Le Master,B. 2002: What Difference Does Difference Make? Negotiating Gender and Generation in Irish Sign Language. In S. Benor, M. Rose, D. Sharma and Q. Shang (eds.): Gendered Practices in Language. Centre for the Study of Languages and Information Publication. Stanford. \par Leonard, C. 2005: Signs of Diversity: Use and Recognition of Gendered Signs among Young Irish Deaf People. Deaf Worlds, Vol. 21 (2) 62-77. \par Volterra, V., S. Laudanna, E. Corazza and F. Natale 1984: Italian Sign Language: The Order of Elements in the Declarative Sentence. In F. Lonke (ed.) Recent Research on European Sign Languages. Svets and Zeitlinger: Lisse. 19- 48.} } @inproceedings{lefebvrealbaret:08007:sign-lang:lrec, author = {Lefebvre-Albaret, Fran{\c c}ois and Gianni, Fr{\'e}d{\'e}rick and Dalle, Patrice}, title = {Toward an computer-aided sign segmentation}, pages = {123--128}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08007.html}, abstract = {Processing sentences of a sign language corpus requires a first step of temporal segmentation, which is long and tedious. To realize this segmentation more quickly, we propose an innovating method of computer-aided segmentation. This method processes motions of the dominated and dominating hands during the sign realisation. The video treatments are applied in four steps. The first one consists in tracking the hands in a video sequence using particles filtering. Then, in a second step, an operator watches the video sequence and indicates for each sign a time stamp during the sign realisation. Using this information and the trajectories of each hand, our method is able to find the beginning and the end of each sign in a third step. At the end, the operator can eventually apply some rectifications and validate the segmentation. \par The presented article explains the different steps, from the calculation of the head and hands 2D positions to the computer-aided determination of the temporal segmentation of the signs. The segmentation exploits a model of French Sign Language and focuses especially on the characteristics of manual sign movements. Our method detects in the video several dynamic properties as the relative hands movement (symmetries, static hands) and the movement primitives (simple or double repetition, uniform or accelerated straight movement). We also detect time spaces between two consecutive signs. Those transitions must be economical, considering the necessary energy to realize these: a movement with a complex realization will contain a sign. Those elements are then combined to each other to determine the most plausible temporal segmentation of the signed sentences. The result can be represented as a succession of signs and transitions segments. \par Other observations can be taken into account to obtain the temporal segmentation. We can mention the determination of the elbows 2D positions, the characterization of hand configurations and the head orientation measurement. We describe how those elements could be used to improve the segmentation reliability. \par The proposed method is based on motion analysis and does not use any knowledge about the words used in the processed sentences. Using the characteristics shared by the majority of French Sign Language's signs, it is possible to detect not only standard signs but also other manual iconic signs. \par Our segmentation results are finally compared with a traditional manual segmentation produced with an annotation software named AnColin. This comparison exhibits several possible error sources. We focus on the problem of granularity and precision of the segmentation. We also discuss about other qualitative problems such as the detection criteria of the signs start and end. The evaluation protocol of a temporal segmentation is also adressed. Finally we will raise several problems to overcome, to realize a fully automatic segmentation.} } @inproceedings{lillomartin:08035:sign-lang:lrec, author = {Lillo-Martin, Diane and Chen Pichler, Deborah}, title = {Development of Sign Language Acquisition Corpora}, pages = {129--133}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08035.html}, abstract = {Longitudinal, spontaneous production data have long been a cornerstone of language acquisition studies, but building corpora of sign language acquisition data poses considerable challenges. Our experience began with the development of a sign language acquisition corpus more than 15 years ago and has recently included a small-scale experiment in corpus sharing between our two research groups. Our combined database includes regular samples of deaf and hearing children between the ages of 1;06 to 3;06 years acquiring ASL as their native language. The process through which we generate and share transcripts has undergone dramatic changes, always with the triple goal of creating transcripts with sufficient information for the reader to locate regions of interest, while keeping the video fully accessible and minimizing the time required to generate transcripts. In this paper we summarize the various incarnations of our transcription system, from simple Word documents with minimal integration of video, to a combination of FileMaker Pro software integrated with Autolog, to a fully integrated transcript+video package in ELAN. Along the way, we discuss the potential of ELAN to surmount several obstacles that have traditionally stood in the way of large-scale corpus sharing in the sign language acquisition community.} } @inproceedings{mesch:08025:sign-lang:lrec, author = {Mesch, Johanna and Wallin, Lars}, title = {Use of sign language materials in teaching}, pages = {134--137}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08025.html}, abstract = {We are in the beginning phase of creating a Swedish Sign Language corpus. Some of the material is now used with students in two separate courses: Swedish Sign Language for beginners, and Swedish Sign Language linguistics (for deaf and hearing signers). In this workshop we will present some teaching methods and technical problems. Some examples are shown of how the students use the sign language corpus through the dictionary database, the corpus database and a learning platform for studying and analyzing sign language texts, like for example the small corpus in Bergman {\&} Mesch 2004 and also some old and new recordings. Students can practice sentences, analyze the entries and annotate the texts or their own recordings. Bergman's earlier transcription system for Swedish Sign Language (Bergman 1982) has been updated continuously, and partly adapted for possible use as a standard annotation system. Problems with storing sign language material are also discussed. \par References \par Bergman, Brita. {\&} Mesch, Johanna. 2004. ECHO data set for Swedish Sign Language (SSL). Department of Linguistics, University of Stockholm. \par Bergman, Brita. 1982. Teckenspr{\aa}kstranskription. Forskning om teckenspr{\aa}k X. Stockholms universitet, Institutionen f{\"o}r lingvistik.} } @inproceedings{moreau:08021:sign-lang:lrec, author = {Moreau, C{\'e}dric and Mascret, Bruno}, title = {{LexiqueLSF}}, pages = {138--140}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08021.html}, abstract = {The French Sign Language (LSF) was banned in 1880 from all teaching institutions. From then on, it continued expanding in an uncoordinated way throughout special schools. In 1991, a new French law allowed deaf people to choose a bilingual education (French and sign language), and since February 2005 each school is required to integrate every devoted child who wishes it, no matter his handicap. All public websites must also become accessible. \par With this new context, the LSF grows using regional differences, and users invent new signs to translate new concepts. However, the sign language cannot count on traditional media to spread out new expressions or words, since it is nor spoken nor written. Therefore the sign vocabulary differs depending on geographical and social situations, furthermore if the concept is specific and elaborate. The website LexiqueLSF wishes to propose users a contributing and efficient tool, allowing a large diffusion of new signs and concepts. A short analysis of the existing supports will lead us to present the main issues and to describe precisely the technical and linguistic solutions we chose, as well as some of the problems we met. This website must absolutely have a relevant and sharp classifying system, must be accessible to everyone, and offer new entries to satisfy all users. Likewise, all the elements composing the website should be considered as a concept in order to imagine complete accessibility to deaf people, and not only to blind people. We do not wish to make a simple dictionary. \par Our aim is to allow exchanges between users, to encourage them to invent and spread neologisms, and to make sure that the represented concepts are clear and understandable. Publishing a new notion requires to create a number of descriptors (in french and in sign language, illustrations, examples...) and to relate this notion to others already existing (opposite or similar concepts...). Each new sign proposed will be completely described, therefore it can easily be appropriated. A reliable, but not compulsory, validation system will guarantee only serious suggestions. \par Our production is thus very different from already existing paper or digital dictionaries, containing only everyday life vocabulary and almost no definitions, nor use examples. The best ones sort words according to the space location and configuration of the sign, but do not recognise morphological variations. Let us also observe that these dictionaries are not "bilingual" since they are accessible only to french speakers. \par According to C. Cuxac 2000, two discursive enunciation strategies co-exist in LSF: through the canal leading from the vision to the sign, you can either choose to say with or without showing. Meaning you can either "make see" your experience with a visually accurate sequence of signs, or you can use the standard signs having no physical resemblance with the experience you are describing. Referring to this theory, our research supposes to organise into a hierarchy all linguistic parameters used in signs as meaning elements.} } @inproceedings{nagashima:08019:sign-lang:lrec, author = {Nagashima, Yuji and Terauchi, Mina and Nakazono, Kaoru}, title = {Construction of {Japanese} {Sign} {Language} Dialogue Corpus: {KOSIGN}}, pages = {141--144}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08019.html}, abstract = {This report presents a method of building corpuses of dialogue in Japanese Sign Language (JSL) and the results of the analysis in co- occurrences of manual and non-manual signals using the corpus. \par We have built the sign dialogue corpus by video recording the dialogues between native JSL speakers. The purpose of building corpus is deriving electronic dictionaries such as morphological dictionary, different meaning word dictionary, allomorph dictionary and example dictionary. Example sentences are recorded for every word (key sign) those were recorded in the sign language word data base KOSIGN Ver.2. Until now, we were able to confirm a correlation of manual and non-manual signals or a characteristic appearance of sign language dialogue. \par As a result of the analysis, the pointing occurred to the end of sentence at high frequency. It suggested that pointing be one of the ends of sentence, and clarified the role as the conjunctive pronoun. The co-occurrence relation between the manual and non-manual signals acquired confirmed an important role to make the meaning of the expression sign language limited was achieved. Moreover, "Roll shift" and "Sandwich construction" that was the linguistic feature of sign language were confirmed, too. These information is necessary for the hearing person to study sign language.} } @inproceedings{nyst:08033:sign-lang:lrec, author = {Nyst, Victoria}, title = {Documenting an Endangered Sign Language: Constructing a Corpus of {Langue} des {Signes} {Malienne} ({CLaSiMa})}, pages = {145--149}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08033.html}, abstract = {Langue des Signes Malienne (LaSiMa) is the local sign language of Mali. It evolved spontaneously in the streets of urban centers outside the context of Deaf education. The Malian `grins', meeting places where men gather in the afternoon to chat and drink tea seem to be the cradle of this language. \par Since about 15 years now, American Sign Language (ASL) has been introduced in Deaf education in Mali. As a consequence, LaSiMa has become the language of non-educated Deaf people and is by many considered to be inferior to ASL. LaSiMa is marginalized and at present, few Deaf adults in Bamako sign LaSiMa without mixing in some ASL signs. It is likely that in few generations, the use of LaSiMa will have reduced or altered greatly. \par Little is known about sign languages from the African continent. In view of the evolution of LaSiMa outside the context of Deaf education in addition to its endangered status, a three-year documentation and description project was set up with the help of the Hans Rausing Endangered Language Program (URL). The aim of the project is to establish a corpus of LaSiMa discourse, a lexical database and descriptions of selected structural aspects of the language. \par The Corpus Langue des Signes Malienne (CLaSiMa) aims at collecting a large, filmed sample of LaSiMa discourse. The sample is to be diverse and representative with respect to its signers (age, gender) and with respect to its discourse types. So far, 15 hours of discourse have been filmed. The filmed discourse is to be translated in French using ELAN software. A selection of the discourse in the corpus will be glossed. The material will be deposited in a digital archive, where it will be accessible through internet for the academic as well as the Malian Deaf community. \par The initial approach to gather the data was inspired by the work on the NGT corpus (Crasborn {\&} Zwitserlood, 2007). Their approach involved among others inviting pairs of signers to a filming location where they discuss preset issues and do specific language-based tasks. A similar approach in the LaSiMa context was challenged in several ways. Controlling the age and gender balance, the ``nativeness'' of signers was problematic as well as the cultural appropriateness of the material and the tasks, affecting the spontaneity of the signers. An alternative approach was developed, which involved recording one or two signers in their `grins'. This required training two native LaSiMa signers in film and interview techniques. \par References \par Onno Crasborn {\&} Inge Zwitserlood (2007) 'The Corpus NGT project: challenges in publishing sign language data'. Workshop 'The emergence of corpus sign language linguistics', paper presented at BAAL 2007, Edinburgh, Thursday 6 Sept. 2007.} } @inproceedings{pizzuto:08014:sign-lang:lrec, author = {Pizzuto, Elena Antinoro and Chiari, Isabella and Rossini, Paolo}, title = {The Representation Issue and its Multifaceted Aspects in Constructing Sign Language Corpora: Questions, Answers, Further Problems}, pages = {150--158}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08014.html}, abstract = {This paper aims to address and clarify one issue we believe is crucial in constructing Sign Languages (SL) corpora: identifying appropriate tools for representing in written form SL productions of any sort, i.e. lexical items, utterances, discourse at large. Towards this end, building on research done within our group on multimedia corpora of both SL and spoken or verbal languages (vl), we first outline some of the major requirements and guidelines followed in current work with vl corpora (e.g. regarding transcription, representation [mark-up], coding [or annotation] Chiari, 2007; Edwards {\&} Lampert; 1993; Leech {\&} al, 1995; Ochs, 1979; Powers, 2005, among others). We highlight that a basic requirement of vl corpora is an easily readable transcription that, aside from specialist linguistic annotations, allows anyone who knows the object language to reconstruct its forms, and its form-meaning correspondences. Second, we show how this basic requirement is not met in most current work on SL, where the `transcription' of SL productions consists primarily of word-labels taken from vl, inappropriately called `glosses'. As argued by some authors (e.g. Pizzuto {\&} Pietrandrea, 2001; Russo, 2005; Pizzuto et al., 2006), the use of such word-labels as a primary representation tool grossly misrepresents SL, even when supported by specialist linguistic annotations (e.g. Stokoe-based notations, the Berkeley Transcription System [Slobin et al., 2001]). Drawing on a crosslinguistic overview of relevant work on SL lexicon and discourse (e.g. Brennan, 2001; Cuxac, 2000; Cuxac {\&} Sallandre, 2007; Russo, 2004; Antinoro Pizzuto et al., 2007), we illustrate how the `transcriptions' most widely used for SL do not allow to anyone who knows the specific SL to reconstruct its forms and form-meaning correspondences, and are especially inadequate for representing complex sign units that are very frequent in SL discourse, and exhibit highly iconic, muldimensional/multilinear features that have no parallel in vl. Third, we present and discuss ongoing research on Italian Sign Language (LIS) in which experienced deaf signers explore the use of SignWriting (Sutton, 1995) as a tool for both composing texts conceived in written form -- thereby creating a corpus of written LIS -- and for transcribing corpora of face-to-face LIS discourse (Di Renzo et al., 2006; Di Renzo, in press; Lamano et al., in press). The results show that, in both cases, deaf signers can easily represent the form-meaning patterns of their language with an accuracy never experienced with other representation or notation systems. The analysis of the texts produced has also provided new indications on the structure of LIS, highlighting the need of revising the criteria for constructing lexical corpora on the grounds of regularities (and variance) found in discourse corpora. While all of this suggests that SignWriting can be a valuable tool for addressing the representation issue in constructing SL corpora, the present computerized form of SignWriting poses technical problems that severely constrain its use. We conclude specifying the problems that need to be faced for conducting more extensive experimentations.} } @inproceedings{prillwitz:08018:sign-lang:lrec, author = {Prillwitz, Siegmund and Hanke, Thomas and K{\"o}nig, Susanne and Konrad, Reiner and Langer, Gabriele and Schwarz, Arvid}, title = {{DGS} {Corpus} Project -- Development of a Corpus Based Electronic Dictionary {German} {Sign} {Language} / {German}}, pages = {159--164}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08018.html}, abstract = {The poster introduces a 15-year project accepted for funding by the Hamburg Academy of Sciences. The proposed project aims to combine the collection of a large corpus with the development and production of a comprehensive, corpus based electronic dictionary of German Sign Language (DGS). \par To this aim, a corpus of approximately 350--400 hours from 250--300 informants will be collected in a variety of elicitation settings. This is, in size and scope, comparable to large spoken language corpora. The design allows the use of the corpus for various tasks. These are, amongst others: (i) the validation by corpus data of a basic vocabulary compiled from different published sources; (ii) research on DGS grammar based on detailed transcription data; (iii) identification of different meanings and collocations of a sign by appropriate contexts. Furthermore, the design anticipates a comparative sociolinguistic study comparable in kind and quality to Lucas et al. (2001) and Schembri/Johnston (2004). The corpus thus provides a starting point for research deep into the structure and lexicon of German Sign Language as well as into the visual-gestural mode of sign languages in general. Parts of the annotated corpus, i.e. transcription files with English translations, will be made available online to the international linguistic community. \par The corpus data will undergo two stages of transcription. First, a basic transcription serves to segment utterances and to identify lexical items and thus provides a first access to the data. Second, approximately 50 {\%} of the transcriptions will be transcribed again in more detail. This serves the purpose of clarifying grammatical questions for the dictionary grammar as well as dealing with lexicological and lexicographic issues. The annotation of the corpus will be closely intertwined with the requirements of lexical analysis. A high quality of transcription will be achieved through continuous verification by native signers. A relational database (iLex, cf. Hanke/Storz) supports this process, especially the consistency of type- token matching. \par Lexical analysis and lexicographic decisions concerning for example lexical status, language change, and lemma selection will be continuously validated by a deaf focus group and a general voting web interface which will be open for all interested members of the deaf community. \par The dictionary will be entirely based on the corpus with respect to the list of lemmas to be included but decidedly exceed a conglomeration of corpus references. Rather, we will systematically abstract from the references to obtain a generalized description of lexical items. Examples of sign uses will be taken directly from the corpus. \par For cross-linguistic research and comparability of results across projects, we consider it essential to push standardisation or at least compatibility of annotation and transcription conventions. To reach this, we have arranged cooperations with some other national corpus projects and look forward to cooperate with more projects currently in preparation. \par References \par Lucas, Ceil / Bayley, Robert / Valli, Clayton (2001): Sociolinguistic Variation in American Sign Language. Washington, DC: Gallaudet Univ. Press. \par Schembri, Adam / Johnston, Trevor (2004): Sociolinguistic variation in Auslan (Australian Sign Language). A research project in progress. In: Deaf Worlds 20 (1), 78-90.} } @inproceedings{schembri:08005:sign-lang:lrec, author = {Schembri, Adam}, title = {{British} {Sign} {Language} {Corpus} Project: Open Access Archives and the Observer's Paradox}, pages = {165--169}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08005.html}, abstract = {The British Sign Language Corpus Project is a new three-year project (2008-2010) that aims to create a machine-readable digital corpus of spontaneous and elicited British Sign Language (BSL) collected from deaf native signers and early learners across the United Kingdom. In the field of sign language studies, it represents a unique combination of methodology from variationist sociolinguistics and corpus linguistics. The project aims to conduct a studies of sociolinguistic variation, language change and language contact simultaneously with the creation of a corpus. As such the nature of the dataset to be collected will be guided by the need to create a judgement sample of the deaf community rather than a strictly representative sample. Although the recruitment of participants will be balanced for gender and age, it will focus only on signers exposed to BSL before the age of 7 years, and adult deaf native signers will be disproportionately represented. Signers will also be filmed in 8 key regions across the United Kingdom, with a minimum of 30 participants from each region. Furthermore, participant recruitment will rely on deaf community fieldworkers in each region, using a technique of `network sampling' in which the local community member begins by recruiting people he or she knows, and asks these individuals to recommend other individuals matching the project criteria. Moreover, the data will be limited in terms of situational varieties, focusing mainly on conversational and interview data, together with narratives and some elicitation tasks. Unlike previous large-scale sociolinguistic projects, however, the dataset will be partly annotated and tagged using ELAN software, given metadata descriptions using IMDI tools, and will be archived and made accessible and searchable on-line. As such, we hope that it will become a standard reference and core data source for all researchers investigating BSL structure and use. This means, however, that, unlike previous sociolinguistic projects on ASL and Auslan, participants must consent to having the video data of their sign language use made public. This seems to put at risk the authenticity of the data collected, as signers may monitor their production more carefully than might otherwise occur. As the aim of variationist sociolinguistics is to study the vernacular variety (i.e., the variety adopted by speakers/signers when they are monitoring their style least closely), open-access archives thus may not always provide the best data source. While recognising that this concept of the vernacular represents an abstraction, we discuss the possibility of overcoming this problem by making some of the conversational data password protected for use by academic researchers only, while making other parts of the corpus publicly available as part of a dual access archive of BSL.} } @inproceedings{schwartz:08032:sign-lang:lrec, author = {Schwartz, Sandrine}, title = {Tactile sign language corpora: capture and annotation issues}, pages = {170--173}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08032.html}, abstract = {Sign language, being a visual-gestural language, can also be used tactually among or with deaf people who become blind. When this language is shared between people who are totally blind, non-manual features of signs are totally neutralised, resulting into a purely kinesthetic-gestural variant of sign language. This tactile modality of reception leads to adjustments impacting sign language pragmatics, as well as sign order and to a lesser extent, the way signs are formed. We aim to explore these phenomena by carrying out a systematic analysis of tactile sign language corpora. \par Such a corpus has been filmed in 2006, involving six French deafblind informants, all of them using tactile sign language as their primary means of communication. A total of 14 hours of spontaneous discussions, free conversations or elicited data were captured by up to three digital cameras. \par In order thoroughly to analyse our corpus, we need the help of a reliable annotation tool. After trying a couple of them, we decided to select Anvil, for its visual layout and flexibility, as well as its temporal granularity. We need a partition annotation system which allows us to create, rename or reorder tracks freely even while annotating. The first steps of our annotation will take us on the lanes of conversational analysis, using a mix of glosses and pragmatic occurrences, eventually to lead us on the more sinuous paths of a syntactic micro-analysis.} } @inproceedings{segouat:08010:sign-lang:lrec, author = {Segouat, J{\'e}r{\'e}mie and Braffort, Annelies and Bolot, Laurence and Choisier, Annick and Filhol, Michael and Verrecchia, Cyril}, title = {Building {3D} {French} {Sign} {Language} lexicon}, pages = {174--177}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08010.html}, abstract = {Sign Language (SL) corpora can be made in vivo (in natural conditions, with or without guidelines) or in vitro (in a laboratory, with guidelines), like speech corpora. While some effort has been made to standardise on corpus metadata with the IMDI project, there is not such norm for SL corpus elaboration: the methodology depends on the research goal. \par Our aim is to create a 3D French SL (LSF) corpus to be used in different types of software, thus the signs must be considered without context. To fit our specific goals, we have decided on the following methodology: \par First of all we look for a referent gestuel: a deaf person, whose first language is LSF and whose signing corresponds to what is needed for the infographic part of the process (see step five). The referent gestuel has been chosen by the team's infographist. It is important to keep the same referent gestuel for all the lexicon, in order to keep a consistency in the 3D corpus. Then, for each scientific topic we consider, we look for an expert: a deaf person, whose first language is FSL and who is aware of the terminology used in the field. Because we want many topics corpus, we work with different experts. Thirdly we organise a meeting with the referent gestuel, the expert and, if necessary, other specialists of the topic we are working on, so they can discuss each meaning of each concept and sign it the as accurately as possible. The next step is to film the referent gestuel two views of the referent gestuel (frontal view and side view). Lastly we animate the 3D avatar by copying each frame of the video, using 3DSMax software. \par This 3D corpus will be used in at least three different informational pieces of software. One that can be used in railway stations to inform deaf users in LSF about the delay of a train or any other problem. Another application will be a dictionary: We are developing a LSF-French dictionary where signs would be given in a the form of a 3D avatar. A third example is to display an Embodied Conversational Agent (ECA) on our laboratory website so that our research topics can be explained in LSF if wanted. \par References \par Michael Filhol, Annelies Braffort et Laurence Bolot (to appear), Signing Avatar: Say hello to Elsi! In: Gesture in Human- Computer Interaction and Simulation, selected revised papers of the 7th International Gesture Workshop (GW'07), LNCS LNAI, Springer. \par Onno Crasborn {\&} Thomas Hanke (2003), Metadata for sign language corpora. Background document for an ECHO workshop, 8 + 9 May 2003, Nijmegen University.} } @inproceedings{tanaka:08016:sign-lang:lrec, author = {Tanaka, Saori and Matsusaka, Yosuke and Nakazono, Kaoru}, title = {Interface Development for Computer Assisted Sign Language Learning: Compact Version of {CASLL}}, pages = {178--184}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08016.html}, abstract = {In this study, we introduce e-learning system called CASLL and demonstrate the small interface in order to implement it into the mobile video reproducers. As one of our series of previous studies for developing human interface by using Japanese Sign Language (JSL) contents [2, 3, 4], we proposed a new learning program and compare it with the existing learning program implemented in the Computer Assisted Sign Language Learning (CASLL) system [1]. In the existing learning program, users learn sign words and then try to select the appropriate Japanese translations in a natural conversation expressed by two native signers. In the proposed program, users try to segment each word from a stream of signing by manipulating a control knob on the bottom of a movie screen, and then do the same tasks in the existing learning model. The end of the segmentation task is to know how continuous signs are articulated in the natural discourse. Ten Japanese learners participated in the experiments. Five subjects learned the existing word learning program and the other five subjects learned the proposed segmentation learning program. The mean accuracy rate of the proposed program was higher than that of the existing program. The result has indicated that focusing on transitional movements has an effect for learning JSL as a second-language. \par Although the segmentation learning method has been shown as more effective learning method compared to the word learning program by which learners need to just memorize the meaning of words, there were some technical problems. Some learners answered that they could not see each JSL movies at once by using their own laptops to conduct the learning programs. Therefore, we needed to improve how to show JSL movies by using different sizes of screen. We define the size of movie screen as small as possible, and develop use-friendly interface with which learners can recognize whole serious of JSL movies by switching each movie side by side. We will demonstrate the interface development and see if the interface is applicable to the other sign languages. \par References \par [1] Saori Tanaka, Yosuke Matsusaka, Kuniaki Uehara: ``Segmentation Learning Method as a Proposal for Sign Language e-learning'', Human Interface, 2006 (in Japanese) \par [2] Saori Tanaka, Kaoru Nakazono, Masafumi Nishida, Yasuo Horiuchi, Akira Ichikawa: Analysis of Interpreter's Skill to Recognize Prosody in Japanese Sign Language, Journal of Japanese Society for Artificial Intelligence (in press). \par [3] Kaoru Nakazono, Saori Tanaka: Study of Spatial Configurations of Equipment for Online Sign Interpretation Service, IEICE Transaction on Information and System (in press) \par [4] Saori Tanaka: A Study of Non-linguistic Information in Japanese Sign Language and its Application for Assisting Learners and Interpreters, Ph.D thesis, Chiba University, 2008} } @inproceedings{zwitserlood:08027:sign-lang:lrec, author = {Zwitserlood, Inge and {\"O}zy{\"u}rek, Asli and Perniss, Pamela}, title = {Annotation of Sign and Gesture Cross-linguistically}, pages = {185--190}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08027.html}, abstract = {In a 5-year project, we compare expressions in the spatial domain between two sign languages (German Sign Language and Turkish Sign Language), the co-speech gestures accompanying two spoken languages (German and Turkish), and the pantomime-like structures used by hearing people (German and Turkish) asked to convey information without speaking. The aim is to discover the similarities and differences in the use of space in expressing referent location and motion between the sign languages, and between the signing, co-speech gesture and no-speech pantomime modes. To this end, we are building a large video corpus of task-related discourse data (about 90 minutes per 15 participants per condition). The data will be described using the IMDI metadata standard and linguistically annotated using ELAN. Parts of the data will be made accessible for research and educational purposes on the Browsable Corpus based at the MPI for Psycholinguistics. \par In this presentation, we report the annotation conventions we have been developing based on collected data. There are two levels of annotation: (i) a descriptive level where we gloss signs and gestures according to the movements/positions of the hands, head, face, and body; and (ii) an analytic/coding level where each sign or gesture is analyzed with respect to the function of establishing and/or maintaining reference in discourse (e.g. through the use of pronouns, classifier predicates, modified verbs, and role shift in signing, and similar forms in gestures). Our conventions combine aspects from other annotation and coding systems developed for sign and gesture (e.g. the ECHO, Corpus NGT, and Auslan Corpus conventions; HamNoSys; gesture coding conventions as developed by Kita, Van Gijn and Van der Hulst), but go beyond them in placing special emphasis on coding both systems with the same parameters. \par On the descriptive level, we developed a 3-dimensional scheme to identify for hand orientation, location, and direction of signs and gestures, allowing comparison across languages. On the analytic/coding level, we devised ways of categorizing how the various spatial expressions in sign and gesture map onto different coreference devices in discourse. \par Parts of the sign and gesture data have now been annotated. We will present some generalizations and conclusions drawn from using our annotation conventions regarding cross-linguistic and sign-gesture comparison. Furthermore, based on our annotation experiences, we will discuss the advantages as well as the shortcomings of our annotation scheme and suggest specific improvements, which the linguistic community needs to consider in terms of ways they can be implemented in the technology of annotation software (such as ELAN).} } @proceedings{lrec:sign-lang:06, editor = {Vettori, Chiara}, title = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, url = {http://www.lrec-conf.org/proceedings/lrec2006/workshops/W15/Sign_Language_Workshop_Proceedings.pdf} } @inproceedings{pizzuto:06001:sign-lang:lrec, author = {Pizzuto, Elena Antinoro and Rossini, Paolo and Russo, Tommaso}, title = {Representing Signed Languages in Written Form: Questions that Need to be Posed}, pages = {1--6}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06001.html}, abstract = {In this paper we discuss some of the major issues linked to the unwritten status of signed languages and to the inadequacy of the notation and transcription tools that are most widely used. Drawing on previous and ongoing research, we propose that the development of a written form appears to be necessary for defining more appropriate representational tools for research purposes.} } @inproceedings{filhol:06002:sign-lang:lrec, author = {Filhol, Michael and Braffort, Annelies}, title = {A Sequential Approach to Lexical Sign Description}, pages = {7--10}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06002.html}, abstract = {Sign description systems able precisely to detail how a lexical unit of a sign language is performed are not that numerous. Plus, in the prospect of implementing such a description model for automatic sign generation by virtual characters, visual notation systems such as SignWriting, however accurate they are, cannot be used. The Hamburg Notation System (HamNoSys) (Hanke, 1989) together with its more computer-friendly super-set SiGML (Signing Gesture Markup Language) is about as advanced a model we could find, and yet some problems still have to be tackled in order to obtain an appropriate sign description system. Indeed, based on Stokoe-type parameters, it assumes every sign can/must be described with the same fixed set of parameters, each of which would be given a discrete value. However, we argue that not all signs require all parameters, and that not all the parameters that are needed can be given at the same time in the same way. This work underlines three problems we see with Stokoe-like descriptions, and suggests a new approach to handling sign language lexicon description.} } @inproceedings{direnzo:06003:sign-lang:lrec, author = {Di Renzo, Alessio and Lamano, Luca and Lucioli, Tommaso and Pennacchi, Barbara and Ponzo, Luca}, title = {{Italian} {Sign} {Language} ({LIS}): Can We Write it and Transcribe it with {SignWriting}?}, pages = {11--16}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06003.html}, abstract = {This paper is the result of our discussions and reflections on using Signwriting for writing and transcribing LIS texts} } @inproceedings{dalle:06004:sign-lang:lrec, author = {Dalle, Patrice}, title = {High Level Models for Sign Language Analysis by a Vision System}, pages = {17--20}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06004.html}, abstract = {Sign language processing is often performed by processing each individual sign and most of existing sign language learning systems focus on lexical level. Such approaches rely on an exhaustive description of the signs and do not take in account the spatial structure of the sentence. We present a high level model of sign language that uses the construction of the signing space as a representation of both (part of) the meaning and the realization of a sentence. We propose a computational model of this construction and explain how it can be attached to a sign language grammar model to help analysis of sign language utterances and to link lexical level to higher levels. We describe the architecture of an image analysis system that performs sign language analysis by means of a prediction/verification approach. A graphical representation can be used to explain sentence construction.} } @inproceedings{zahedi:06005:sign-lang:lrec, author = {Zahedi, Morteza and Dreuw, Philippe and Rybach, David and Deselaers, Thomas and Bungeroth, Jan and Ney, Hermann}, title = {Continuous Sign Language Recognition -- Approaches from Speech Recognition and Available Data Resources}, pages = {21--24}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06005.html}, abstract = {In this paper we describe our current work on automatic continuous sign language recognition. We present an automatic sign language recognition system that is based on a large vocabulary speech recognition system and adopts many of the approaches that are conven- tionally applied in the recognition of spoken language. Furthermore, we present a set of freely available databases that can be used for training, testing and performance evaluation of sign language recognition systems. First results on one of the databases are given, we show that the approaches from spoken language recognition are suitable, and we give directions for further research.} } @inproceedings{infantino:06006:sign-lang:lrec, author = {Infantino, Ignazio and Rizzo, Riccardo and Gaglio, Salvatore}, title = {A Software System for Automatic Signed {Italian} Recognition}, pages = {25--30}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06006.html}, abstract = {The paper shows a system for automatic recognition of Signed Italian sentences. The proposed system is based on a multi-level architecture that models and manages the knowledge involved in the recognition process in a simple and robust way, integrating a common sense engine in order to deal with sentences in their context. In this architecture, the higher abstraction level introduces a semantic control and an analysis of the correctness of a sentence given a sequence of previously recognized signs. Experimentations are presented using a set of signs from the Italian Sign Language (LIS) and a sentence template useful for domotic applications, and show a high recognition rate that encourages to investigate on larger set of sign and more general contexts.} } @inproceedings{garcia:06007:sign-lang:lrec, author = {Garcia, Brigitte}, title = {The Methodological, Linguistic and Semiological Bases for the Elaboration of a Written Form of {French} {Sign} {Language} ({LSF})}, pages = {31--36}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06007.html}, abstract = {This paper takes up the question of elaborating a graphical representation for French Sign language (LSF), beginning with the specificities of the socio-cultural context in which this question arises for those most directly concerned, that is the Deaf. We underline especially the vigilance required, when confronted with the influence of the written form of the Vocal language on linguistic (and therefore graphical) representations of Sign language (SL). We then present the results of a field survey, which allow us to justify and define our objective: write and not transcribe LSF. Next we explain precisely how the admitted limitations of current graphical systems for SL call into question the validity of the principles of segmentation adopted by consensus, which results from the influence of model of dominant alphabetical writing systems and of the focalisation only on lexical signs taken out of context, at the expense of the structural specificities of SL. We present on these bases the major principles of the alternative method begun for LSF, based on the descriptive model proposed by Cuxac (2000). We wish in particular to explore and evaluate his hypothesis of low-level morpho-phonetic segmentation, thus opening the way for an at least partial morphemographic representation.} } @inproceedings{kellettbidoli:06008:sign-lang:lrec, author = {Kellett Bidoli, Cynthia J.}, title = {Glossary Compilation of {LSP} Including a Signed Language: a Corpus-based Approach}, pages = {37--42}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06008.html}, abstract = {Sign language interpreters not only work in a `community' context but also are called to conferences on deafness-related issues containing language for special purposes (LSP). In Trieste, within an Italian national research project, one particular area of research has been centred on investigating textual recasting that may take place during English to Italian Sign Language (LIS) interpretation based on the compilation of parallel multimodal corpora in English, Italian and LIS. Electronic analysis of the corpora enabled the collecting and concordancing of specialized terminology and the development of a pilot version of a trilingual electronic terminological dictionary (on CD-ROM). The glossary will contain dynamic imagery of LIS and will provide a useful and innovative tool for future interpreter trainees.} } @inproceedings{denardi:06009:sign-lang:lrec, author = {Denardi, R{\'u}bia Medianeira and Blauth Menezes, Paulo Fernando and Costa, Ant{\^o}nio Carlos da Rocha}, title = {An Animator of Gestures Applied to Sign Languages}, pages = {43--48}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06009.html}, abstract = {Motivated for to the expansion of the Internet and the increasing development of Web technologies and for a great number of people with distinct necessities search at that the information they need, we try to attend the deaf community by development an Animator of Gestures applied to the Sign Languages, the AGA-Sign, with the goal of assisting practical writing of signs and in the familiarization with the language. This work presents an application for automatized generation of animations of gestures applied to the Sign Languages from texts written in SignWriting. The used signs for the development of the application had been elaborated from the LIBRAS and the animations had been generated through model AGA (graphical animation based in the Automata Theory).} } @inproceedings{efthimiou:06010:sign-lang:lrec, author = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Sapountzaki, Galini}, title = {Processing Linguistic Data for {GSL} Structure Representation}, pages = {49--54}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06010.html}, abstract = {The here presented work reports on incorporation of a core grammar of Greek Sign Language (GSL) into a Greek to GSL conversion tool. The output of conversion feeds a signing avatar, enabling dynamic sign synthesis. Efficient conversion is of significant importance in order to support access to e-content by the Greek deaf community, given that the conversion tool may well be integrated into various applications, which require linguistic knowledge. The converter is built upon standard principles of Machine Translation (MT) and matches Greek parsed input to equivalent GSL output. The transfer module makes use of NLP techniques to enrich linear sign concatenation with GSL-specific complex features uttered both manually and non-manually. GSL features are either checked against properties coded in a lexicon DB for base signs or they are generated by grammar rules. The GSL computational grammar is based on natural data analysis in order to capture the generative characteristics of the language. The conversion grammar of the transfer module, however, makes use of a number of heuristic solutions. This is implicated by the type of input for conversion, which derives from a statistical shallow parser, so that various semantic features have to be retrieved by mere grouping of lemmata. However, this type of input is directly connected with the requirement for fast processing of vast amounts of linguistic information.} } @inproceedings{costa:06011:sign-lang:lrec, author = {Costa, Ant{\^o}nio Carlos da Rocha and Dimuro, Gra{\c c}aliz Pereira and Bedregal, Benjamin C.}, title = {Recognizing Hand Gestures Using a Fuzzy Rule-Based Method and Representing them with {HamNoSys}}, pages = {55--58}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06011.html}, abstract = {This paper introduces a fuzzy rule-based method for the recognition of hand gestures acquired from a data glove, and a way to show the recognized hand gesture using the graphical symbols provided by the HamNoSys notation system. The method uses the set of angles of finger joints for the classification of hand configurations, and classifications of segments of hand gestures for recognizing gestures. The segmentation of gestures is based on the concept of "monotonic" gesture segment, i.e., sequences of hand configurations in which the variations of the angles of the finger joints have the same tendency (either non-increasing or non-decreasing), separated by reference hand configurations that mark the inflexion points in the sequence. Each gesture is characterized by its list of monotonic segments. The set of all lists of segments of a given set of gestures determine a set of finite automata that recognize such gestures. For each gesture, a sequence of HamNoSys symbols representing the reference hand configurations of the gesture is produced as an output.} } @inproceedings{aznar:06012:sign-lang:lrec, author = {Aznar, Guylhem and Dalle, Patrice}, title = {Analysis of the Different Methods to Encode {SignWriting} in Unicode}, pages = {59--63}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06012.html}, abstract = {This paper lists, evaluates and discuss the solutions to encode SW in Unicode. SignWriting is the most complex and popular writing formalism for sign languages. Unicode is the most popular encoding of characters aimed at unifying the various language-oriented encodings into a single format supporting every human language. This paper focuses on the first functional layer, which gives a correspondence between a SignWriting sign and a series of bytes. This is one of the prerequisites to represent a sign language electronically. The different possibilities to encode a given SignWriting sign are evaluated and compared on different criteria : the Unicode space requirements, the number of bytes the storage will require, the mathematical complexity and the side advantages offered. Keeping as much as possible of the information on how signs are written and entered, and offering capabilities to easily compare the symbols that compose these signs is also considered, so that the encoding can serve to study and compare how SignWriting is written. A reference encoding is then proposed, to serve as a basis for the next layers. Other bi-dimensional writing formalisms, currently not supported by Unicode, are considered to extend the presented work.} } @inproceedings{mertzani:06013:sign-lang:lrec, author = {Mertzani, Maria}, title = {Sign Language Learning through Asynchronous Computer Mediated Communication}, pages = {64--69}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06013.html}, abstract = {Current research shows that CMC provides an excellent vehicle for L2 learning since it affords both teachers and learners to communicate in an authentic learning environment where negotiation of meaning in the target language can take place in the same way as in face-to-face interaction. As bandwidth networks become more developed, it is feasible to transmit sign language communication using digitised video. In this paper, I present SignLab, a virtual sign laboratory at the Centre for Deaf Studies (CDS), in Bristol University, U.K., developed through the use of `Panda' software. It is an asynchronous videoconferencing system developed for the learning of British Sign Language. In this paper, I discuss how SignLab changes the concept of traditional sign language teaching and learning in terms of course delivery, tutors' and students' online roles, course material and online communication and collaboration. At the end, I propose a framework based on constructivist and learner-centred principles that teachers may consider applying when teaching online.} } @inproceedings{hanke:06014:sign-lang:lrec, author = {Hanke, Thomas}, title = {Towards a Corpus-based Approach to Sign Language Dictionaries}, pages = {70--73}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06014.html}, abstract = {This paper discusses those aspects of iLex, a sign language transcription tool, that are relevant to lexical work and the production of e- learning materials. iLex is built upon a relational database, and uses this strength to support the user in type-token matching by giving immediate access to all other tokens already related to a certain type. iLex features a number of classification schemes, both built-in and data-driven, to allow for the incremental process of identifying and describing the lexicon of a sign language. Data cannot only be exported to other transcription tools, but also into authoring systems for teaching materials. Finally, we speculate about the applicability of Zipf's Law for sign language corpora extrapolating from the current contents of the iLex database.} } @inproceedings{pleissner:06015:sign-lang:lrec, author = {Pleissner, Sandy}, title = {Translation of Natural Speech into Sign Language Based on Semantic Relations}, pages = {74--77}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06015.html}, abstract = {Based on speech observations in children and categories of semantic classes we designed a system which identifies these in natural language and translates them into a sign language. To accomplish this translation, we use algorithms to annotate a set of semantic relations in children's language and hope to regain these sentences from natural source sentences. We define a set of rules used to change the word sequence of origin sentences at every marked relation.} } @inproceedings{braffort:06016:sign-lang:lrec, author = {Braffort, Annelies}, title = {Articulatory Analysis of the Manual Parameters of the {French} {Sign} {Language} Conventional Signs}, pages = {78--81}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06016.html}, abstract = {This paper presents results of the analysis of French Sign Language (LSF) conventional signs that have been extracted from a LSF dictionary, in order to help the design of LSF processing systems. The signs (more than 1200) have been described, regarding manual parameters from an articulatory point of view. The movement parameter has been considered regarding the moving articulator: hand, wrist, and forearm. Thus, handshape, orientation and location parameters have been considered to be static or dynamic. The descriptions have been stored in a database, allowing us to compute quantitative data for each parameter and for the links between the parameters. Our analysis on this database gives us clues to design new description systems of lexical signs for SL processing, for automatic recognition or generation with the aim to design more accurate and synthetic representations.} } @inproceedings{crasborn:06017:sign-lang:lrec, author = {Crasborn, Onno and Sloetjes, Han and Auer, Eric and Wittenburg, Peter}, title = {Combining Video and Numeric Data in the Analysis of Sign Languages within the {ELAN} Annotation Software}, pages = {82--87}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06017.html}, abstract = {This paper describes hardware and software that can be used for the phonetic study of sign languages. The field of sign language phonetics is characterised, and the hardware that is currently in use is described. The paper focuses on the software that was developed to enable the recording of finger and hand movement data, and the additions to the ELAN annotation software that facilitate the further visualisation and analysis of the data.} } @inproceedings{mertzani:06018:sign-lang:lrec, author = {Mertzani, Maria and Denmark, Clark and Day, Linda}, title = {Forming Sign Language Learning Environments in Cyberspace}, pages = {88--91}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06018.html}, abstract = {In this paper we would like to present the way virtual learning environments (VLEs) are employed into the teaching and learning of British Sign Language (BSL) at the Centre for Deaf Studies of Bristol University, U.K. By considering cyberspace a culturally constructed environment where people can form different virtual communities, this paper will focus on the creation of a virtual learning community for the purposes of BSL learning. Both tutors and students have access and meet on two main websites: SignStation and DeafStation, from where they can retrieve authentic BSL material during their classes and interact through a videoconferencing software system, Panda. We describe the development of VLE and discuss the practices employed when meeting online in terms of instruction delivery and knowledge construction.} } @inproceedings{insolera:06019:sign-lang:lrec, author = {Insolera, Emilio and Militano, Maria Giuseppina and Radutzky, Elena and Rossini, Alessandra}, title = {Pilot Learning Strategies in Step with New Technologies: {LIS} and {Italian} in a Bilingual Multimedia Context `Tell Me a Dictionary'}, pages = {92--95}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06019.html}, abstract = {A pilot project designed for the integrated or non-integrated classroom, speech therapy setting, and family at home, this multi-media DVD + book series offers deaf and hearing children ``of all ages'' a lively interactive tool for discovering and comparing two very different languages, Italian Sign Language and Italian. \par ``Raccontami un dizionario''(Tell Me A Dictionary) is rich in vocabulary presented through stories and sentences that project both languages as living languages, thanks also to a lively 8-minute animated cartoon, signed and spoken narration, Italian with subtitles, vocabulary building games and a glossary that takes you back to the vocabulary items in the DVD. \par The illustrations and story in the accompanying book derive from the DVD: both animated and printed versions tell the story even without the support of language, permitting access even to young children just beginning to read. \par The animated story facilitates the understanding of written Italian, especially verbs which, through animation, offer a dynamism that is limited by two dimensional book illustrations. The book reinforces the written Italian and children can experiment narrating the story to their friends and engage in dramatization with classmates. \par Published by LisMedia {\&} CO, it is easily adapted to other spoken and signed languages.} } @inproceedings{cameracanna:06020:sign-lang:lrec, author = {Cameracanna, Emanuela and Franchi, Maria Luisa}, title = {Metodo Vista -- Teaching Sign Language in {Italy}}, pages = {96--99}, editor = {Vettori, Chiara}, booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios}, maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {28}, month = may, year = {2006}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06020.html}, abstract = {The Metodo VISTA is a video course consisting of a Teacher's Book and a Teacher's Video, a Student's Book and a Student's Video. It is based on the book ``Signing Naturally'' for the teaching of American Sign Language written by Chery Smith, Ella Mae Lentz and Ken Mikos, and has been adapted for the teaching of LIS. Thus the first, second and third volume are intended for teachers who wish to teach LIS and for students who want to learn it. Its aim is to help teachers organize a series of lessons divided into three different levels of language learning. The Metodo VISTA leads the students who know nothing about deafness or Sign Language to interact with deaf people in a wide range of situations. The knowledge of the culture of the deaf is an integral part of the programme. It is also taught by the presentation of native signers who show cultural and linguistic behaviour in various situations in a video.} } @proceedings{lrec:sign-lang:04, editor = {Streiter, Oliver and Vettori, Chiara}, title = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, url = {http://www.lrec-conf.org/proceedings/lrec2004/ws/ws18.pdf} } @inproceedings{hanke:04001:sign-lang:lrec, author = {Hanke, Thomas}, title = {{HamNoSys} -- Representing Sign Language Data in Language Resources and Language Processing Contexts}, pages = {1--6}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04001.html}, abstract = {This paper gives a short overview of the Hamburg Notation System for Sign Languages (HamNoSys) and describes its application areas in language resources for sign languages and in sign language processing.} } @inproceedings{gleaves:04003:sign-lang:lrec, author = {Gleaves, Richard and Sutton, Valerie}, title = {{SignWriter}}, pages = {7--12}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04003.html}, abstract = {This paper reviews the design history of SignWriter, a word processor for the SignWriting system. While the primary goal of SignWriter was simply to create a word processor for SignWriting, its development and subsequent use had several beneficial effects on the SignWriting system. Various design aspects of SignWriter are considered in the context of current computing technologies and sign processing development efforts.} } @inproceedings{sapountzaki:04004:sign-lang:lrec, author = {Sapountzaki, Galini and Efthimiou, Eleni and Karpouzis, Costas and Kourbetis, Vassilis}, title = {Open-ended Resources in {Greek} {Sign} {Language}: Development of an e-Learning Platform}, pages = {13--19}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04004.html}, abstract = {In this paper we present the creation of dynamic linguistic resources of Greek Sign Language (GSL). The resources will feed the development of an educational multitask platform within the SYNENNOESE project for the teaching of and in GSL. The platform combines avatar and animation technologies for the production of sign sequences/streams, exploiting digital linguistic resources of both lexicon and grammar of GSL. In SYNENNOESE, the input is written Greek text, which is then transformed into GSL and appears animated on screen. A syntactic parser decodes the structural patterns of written Greek and matches them into equivalent patterns in GSL, which are then signed by a virtual human. The adopted notation system for the lexical database is HamNoSys (Hamburg Notation System). For the implementation of the digital signer tool, the signer's synthetic movement follows MPEG-4 standard and frame H-Anim with the use of VRML language.} } @inproceedings{crasborn:04005:sign-lang:lrec, author = {Crasborn, Onno and van der Kooij, Els and Broeder, Daan and Brugman, Hennie}, title = {Sharing sign language corpora online: proposals for transcription and metadata categories}, pages = {20--23}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04005.html}, abstract = {This paper presents the results of a European project called ECHO, which included an effort to publish sign language corpora online. The aim of the ECHO project was to explore the intricacies of sharing data using the internet in all areas of the humanities. For sign language, this involved adding a specific profile to the IMDI metadata set for characterizing spoken language corpora, and developing a set of transcription conventions that are useful for a broad audience of linguists. In addition to presenting these results, we outline some options for future technological developments, and bring forward some ethical problems relating to publishing video data on internet.} } @inproceedings{huenerfauth:04006:sign-lang:lrec, author = {Huenerfauth, Matt}, title = {Spatial Representation of Classifier Predicates for Machine Translation into {American} {Sign} {Language}}, pages = {24--31}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04006.html}, abstract = {The translation of English text into American Sign Language (ASL) animation tests the limits of traditional machine translation (MT) approaches. The generation of spatially complex ASL phenomena called ``classifier predicates'' motivates a new representation for ASL based on virtual reality modeling software, and previous linguistic research provides constraints on the design of an English-to- Classifier-Predicate translation process operating on this representation. This translation design can be incorporated into a multi- pathway architecture to build English-to-ASL MT systems capable of producing classifier predicates.} } @inproceedings{costa:04007:sign-lang:lrec, author = {Costa, Ant{\^o}nio Carlos da Rocha and Dimuro, Gra{\c c}aliz Pereira and Baldez de Freitas, Juliano}, title = {A Sign Matching Technique to Support Searches in Sign Language Texts}, pages = {32--36}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04007.html}, abstract = {This paper presents a technique for matching two signs written in the SignWriting system. We have defined such technique to support procedures for searching in sign language texts that were written in that writing system. Given the graphical nature of SignWriting, a graphical pattern matching method is needed, which can deal in controlled ways with the small graphical variations writers can introduce in the graphical forms of the signs, when they write them. The technique we present builds on a so-called degree of graphical similarity between signs, allowing for a sort of ``fuzzy'' graphical pattern matching procedure for written signs.} } @inproceedings{herrero:04008:sign-lang:lrec, author = {Herrero, Angel}, title = {A Practical Writing System for Sign Languages}, pages = {37--42}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04008.html}, abstract = {This paper discusses the problems involved in writing sign languages and explains the solutions offered by the Alphabetic Writing System (Sistema de Escritura Alfab{\'e}tica, S.E.A.) developed at the University of Alicante in Spain. We will ponder the syllabic nature of glottographic or phonetically-based writing systems, and will compare practical phonological knowledge of writing with notions of syllables and sequence. Taking advantage of the ideas of sequentiality contributed by the phonology of sign languages, we will propose a sequential writing model that can represent signers' practical phonological knowledge.} } @inproceedings{papadogiorgaki:04009:sign-lang:lrec, author = {Papadogiorgaki, Maria and Grammalidis, Nikos and Sarris, Nikos and Strintzis, Michael G.}, title = {Synthesis of Virtual Reality Animations from {SWML} using {MPEG-4} Body Animation Parameters}, pages = {43--50}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04009.html}, abstract = {This paper presents a novel approach for generating VRML animation sequences from Sign Language notation, based on MPEG-4 Body Animation. Sign Language notation, in the well-known SignWriting system, is provided as input and is initially converted to SWML (SignWriting Markup Language), an XML-based format which has recently been developed for the storage, indexing and processing of SignWriting notation. Each sign box (basic sign) is then converted to a sequence of Body Animation Parameters (BAPs) of the MPEG-4 standard, corresponding to the represented gesture. These sequences, which can also be coded and/or reproduced by MPEG-4 BAP players, are then used to animate H-anim compliant VRML avatars, reproducing the exact gestures represented in sign language notation. Envisaged applications include producing signing avatars for interactive information systems (Web, E-mail, info-- kiosks) and TV newscasts for persons with hearing disabilities.} } @inproceedings{efthimiou:04010:sign-lang:lrec, author = {Efthimiou, Eleni and Vacalopoulou, Anna and Fotinea, Stavroula-Evita and Steinhauer, Gregory}, title = {Multipurpose Design and Creation of {GSL} Dictionaries}, pages = {51--58}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04010.html}, abstract = {In this paper we present the methodology of data collection and implementation of databases with the purpose to create extensive lexical and terminological resources for the Greek Sign Language (GSL). The focus is on issues of linguistic content validation, multipurpose design and reusability of resources, exemplified by the multimedia dictionary products of the projects NOEMA (1999- 2001) and PROKLISI (2002-2004). As far as data collection methodology, DB design and resources development are concerned, a clear distinction is made between general language lexical items and terms, since the creation of resources for the two types of data undergoes different methodological principles, lexeme formation and usage conditions. There is also reference to content and interface evaluation mechanisms, as well as to basic linguistic research carried out for the support of lexicographical work.} } @inproceedings{vettori:04011:sign-lang:lrec, author = {Vettori, Chiara and Streiter, Oliver and Knapp, Judith}, title = {From Computer Assisted Language Learning ({CALL}) to Sign Language Processing: the Design of {E-LIS}, an Electronic Bilingual Dictionary of {Italian} {Sign} {Language} and {Italian}}, pages = {59--62}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04011.html}, abstract = {This paper presents the design of e-LIS (Electronic Bilingual Dictionary of Italian Sign Language (LIS) and Italian), an ongoing research project at the European Academy of Bolzano. We will argue that an electronic sign language dictionary has to fulfil the function of a reference dictionary as well as the function of a learner's dictionary. We therefore provide an analysis of CALL approaches and technologies, taking as example the CALL systems ELDIT and GYMN@ZILLA developed at the European Academy of Bolzano too. We will show in how far these approaches or techniques can be ported to create an electronic dictionary of sign languages, for which system components new solutions have to be found and whether specific modules for the processing of sign languages have to be integrated.} } @inproceedings{nogueira:04012:sign-lang:lrec, author = {Nogueira, Rub{\'e}n and Mart{\'i}nez, Jose M.}, title = {19th Century Signs in the Online {Spanish} {Sign} {Language} Library: the Historical Dictionary Project}, pages = {63--67}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04012.html}, abstract = {This paper will illustrate the work made in the Sign Language Virtual Library (http://www.cervantesvirtual.com/portal/signos), a project aimed at people interested in Spanish Sign Language; and specially, at its main users, Deaf people. It is organised into six different sections: Literature, Linguistics, researchers forum, Deaf culture and community, bilingual-bicultural education and didactic materials. Each section contains different publications related to the above mentioned areas. Moreover, in this web you will also find an innovation, since every publication includes a summary in Spanish sign language. Two sections will be described: The Historical Dictionary published by Francisco Fernandez Villabrille and the Alphabetical Writing Lessons. Our intention is showing a full functional version of the applications described on the paper.} } @inproceedings{ochse:04013:sign-lang:lrec, author = {Ochse, Elana}, title = {A language via two others: learning {English} through {LIS}}, pages = {68--74}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04013.html}, abstract = {The complex intercultural activity of teaching/learning to read and write in a foreign language clearly involves a reciprocal cultural exchange. While trying to get students to efficiently learn the language in question, namely English, the teacher adapts to her pupils' culture and communication mode: in this case LIS or Italian Sign Language. \par This paper attempts to demonstrate the complex process of developing a corpus for analysis of selected foreign language classroom exchanges. Here our emphasis is on face-to-face communication: what is imparted to the students by the teacher in Italian, how this information is transmitted or filtered by the LIS interpreter, what information the students eventually receive and how they react to it. A particular example of classroom activity has been filmed, transcribed and analysed from the points of view of successful communication, on the one hand, and failure or breakdown of exchange, on the other.} } @inproceedings{roald:04014:sign-lang:lrec, author = {Roald, Ingvild}, title = {Making Dictionaries of Technical Signs: from Paper and Glue through {SW-DOS} to {SignBank}}, pages = {75--78}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04014.html}, abstract = {Teaching mathematics and physics in upper secondary school for the deaf since 1975, this author has felt the need to collect signs for the various concepts. In the beginning illustration of signs were pasted into a booklet. Then SignWriting appeared, and signs were hand-written and later typed into the booklet. With the 3.1 version of SignWriter, the dictionary program appeared, and several thematic dictionaries were made. With the new SignBank program, there are new opportunities, and I can fill in what I before just had to code. Last year a Fulbright research fellow and myself were collecting signs for mathematics, and these are transferred into a SignBank file. From that file various ways of sorting and analysing is possible. Here these various stages are presented, with a focus especially on the SignBank and the opportunities and limitations that are present in this program.} } @inproceedings{aerts:04015:sign-lang:lrec, author = {Aerts, Steven and Braem, Bart and Van Mulders, Katrien and De Weerdt, Kristof}, title = {Searching {SignWriting} Signs}, pages = {79--81}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04015.html}, abstract = {At the moment the publication of the first written Flemish Sign Language (VGT) Dictionary is in progress. It consists of VGT glossaries and allows its users to lookup the signs for over 2000 Dutch words. The signs are written in SignWriting. \par We have established an electronic representation of this sign language dictionary. Searching for signs starting from a Dutch word works straightforward. The opposite, receiving results ordered by relevance, has never been develloped before. In this paper we explain how we have worked out such a system.} } @inproceedings{zwitserlood:04016:sign-lang:lrec, author = {Zwitserlood, Inge and Hekstra, Doeko}, title = {Sign Printing System -- {SignPS}}, pages = {82--84}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04016.html}, abstract = {The development of the Sign Printing System (SignPS) is based on the need of a way for sign language users and teachers to compose pictures of signs without having considerable drawing skills, to store these pictures into a database and to retrieve them at wish for several purposes. The sign pictures are abstract but nevertheless recognizeable without specific training. The programme is not developed for scientific purposes, but for use by the general (signing) public.} } @inproceedings{lenseigne:04017:sign-lang:lrec, author = {Lenseigne, Boris and Gianni, Fr{\'e}d{\'e}rick and Dalle, Patrice}, title = {A New Gesture Representation for Sign Language Analysis}, pages = {85--90}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04017.html}, abstract = {Computer aided human gesture analysis requires a model of gestures, and an acquisition system which builds the representation of the gesture according to this model. In the specific case of computer Vision, those representations are mostly based on primitives described from a perceptual point of view, but some recent issues in Sign language studies propose to use a proprioceptive description of gestures for signs analysis. As it helps to deal with ambiguities in monocular posture reconstruction too, we propose a new representation of the gestures based on angular values of the arm joints based on a single-camera computer vision algorithm.} } @inproceedings{hernandezrebollar:04018:sign-lang:lrec, author = {Hernandez-Rebollar, Jose L.}, title = {Phonetic Model for Automatic Recognition of Hand Gestures}, pages = {91--94}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04018.html}, abstract = {This paper discusses a phonetic model of hand gestures that leads to automatic recognition of isolated gestures of the American Sign Language by means of an electronic instrument. The instrumented part of the system combines an AcceleGlove and a two-link arm skeleton. The model brakes down hand gestures into unique sequences of phonemes called Poses and Movements. Recognition system was trained and tested on volunteers with different hand sizes and signing skills. The overall recognition rate reached 95{\%} on a lexicon of 176 one- handed signs. The phonetic model combined with the recognition algorithm allows recognition of new signs without retraining.} } @inproceedings{noelpp:04019:sign-lang:lrec, author = {Noelpp, Daniel Thomas Ulrich}, title = {Development of a New ``{SignWriter}'' Program}, pages = {95--97}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04019.html}, abstract = {The ``Sutton SignWriting'' system is a practical writing system for deaf sign languages. The symbols describe shape, location and movement of hands as well facial expressions and other signing information. ``SignWriter Java 1.5/Swing'' is being developed as the successor to ``SignWriter DOS'', a program for typing and editing ``SignWriting'' texts, used by school children, teachers, linguists and Deaf people. The new Java version 1.5 ``Tiger'' is used in development and Swing as the graphical user interface.} } @inproceedings{elliott:04020:sign-lang:lrec, author = {Elliott, Ralph and Glauert, John and Jennings, Vince and Kennaway, Richard}, title = {An Overview of the {SiGML} Notation and {SiGMLSigning} Software System}, pages = {98--104}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04020.html}, abstract = {We present an overview of the SiGML notation, an XML application developed to support the definition of Sign Language sequences for performance by a computer-generated virtual human, or avatar. We also describe SiGMLSigning, a software framework which uses synthetic animation techniques to provide real-time animation of sign language sequences expressed in SiGML.} } @inproceedings{bungeroth:04021:sign-lang:lrec, author = {Bungeroth, Jan and Ney, Hermann}, title = {Statistical Sign Language Translation}, pages = {105--108}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04021.html}, abstract = {In the field of machine translation, significant progress has been made by using statistical methods. In this paper we suggest a statistical machine translation system for Sign Language and written language, especially for the language pair German Sign Language (DGS) and German. After introducing the system's architecture, statistical machine translation in general and notation systems for Sign Language, the corpus processing is scetched. Finally, preliminary translation results are presented.} } @inproceedings{aznar:04022:sign-lang:lrec, author = {Aznar, Guylhem and Dalle, Patrice}, title = {Computer Support for {SignWriting} Written Form of Sign Language}, pages = {109--110}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04022.html}, abstract = {Signwriting's thesaurus is very large. It consists of 425 basic symbols, split in 60 groups from 10 categories. Each basic symbol can have 4 different representations, 6 different fillings and 16 different spatial rotations.} } @inproceedings{chen:04023:sign-lang:lrec, author = {Chen, Yiqiang and Gao, Wen and Yang, Changshui and Jiang, Dalong and Ge, Cunbao}, title = {{Chinese} {Sign} {Language} Synthesis and Its Applications}, pages = {111--112}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04023.html}, abstract = {The Sign Language is the communication language for deaf-mute community. Everywhere in the world may have their own sign language. There are over 20.57 million deaf people with thousand kinds of language in China. Hence a set of standard Chinese Sign language for the Deaf-Mute has been revised several times by Chinese Deaf-mute Association supported by the Chinese Government. The updated standard Chinese sign language will help you easily communicate with any deaf people in China.} } @inproceedings{laterza:04024:sign-lang:lrec, author = {Laterza, Paola and Baj, Claudio}, title = {Progetto {e-LIS@}}, pages = {113--125}, editor = {Streiter, Oliver and Vettori, Chiara}, booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication}, maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {30}, month = may, year = {2004}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04024.html}, abstract = {Progetto e-LIS@ is the presentation of a work-in- progress, which was started in November 2000 by two Italian scholars, Paola Laterza (who is a hearing psychologist) and Claudio Baj, a Deaf LIS teacher. Their aim is to find a system of cataloguing signs in order to create a complete but flexible multimedial dictionary, to be used both by competent Italian Sign Language users and by competent users of Italian. This research presents a new way of ordering signs, different from the usual alphabetical one, and is more congenial to the signing community's linguistic needs, which are clearly oriented to the visual-corporeal channel rather than to the written- oral one. In fact, there are Italian/Sign Language dictionaries based on the alphabetical order, but there is none that goes from Sign Language to the written-oral language (Italian). Special attention has been paid to how signs are systematised: so far the handshape parameter has been explored in detail, but in the near future we plan to associate it with two more parameters, viz. location and orientation. At a later date movement and non-manual signals will also be included among the cataloguing criteria. The objective is not only to put signs in order according to a more flexible and therefore acceptable system for signers (like the alphabetical order satisfies hearing people's phonological needs), but also to allow for the quick search of signs in the multimedial dictionary. The paper describes how, after elaborating different versions in their step-by-step research, the two researchers decided that the present format was more functional, practical and economical from the point of view of the dictionary as an instrument. They will present the results already obtained in their research as well as their intermediate findings to demonstrate their chosen work method but also to receive feedback from other Italian and European realities.} } @inproceedings{maximo-chiruzzo-2026-poses:lrec, author = {M{\'a}ximo, Santiago and Chiruzzo, Luis}, title = {Generating Sign Language Poses from {HamNoSys} and Natural Language Descriptions}, pages = {9358--9367}, editor = {Piperidis, Stelios and Bel, N{\'u}ria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio}, booktitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {11--16}, month = may, year = {2026}, isbn = {978-2-493814-49-4}, language = {english}, url = {https://lrec.elra.info/lrec2026-main-735}, doi = {10.63317/466di7tv7dpd}, abstract = {One of the steps involved in the process of sign language generation is generating a sequence of poses that represent the signs. This paper presents a method for using textual information to improve the translation of signs in HamNoSys format into sequences of poses. The method comprises a description generator that translates HamNoSys into a textual description, an LLM fine-tuned to the task of predicting a pose sequence from a HamNoSys description, and a VQ-VAE network that encodes and decodes pose sequences as a list of discrete symbols. Our experiments found that even using simple dictionary descriptions of HamNoSys, it is possible to improve the predictions of pose sequences by leveraging the information from a pretrained LLM.} } @inproceedings{saha-etal-2026-banglasl:lrec, author = {Saha, Neelavro and Shahriyar, Rafi and Roudra, Nafis Ashraf and Sakib, Saadman and Rasel, Annajiat Alim}, title = {Introducing a {Bangla} {Sentence--Gloss} Pair Dataset for {Bangla} {Sign} {Language} Translation and Research}, pages = {10457--10466}, editor = {Piperidis, Stelios and Bel, N{\'u}ria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio}, booktitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {11--16}, month = may, year = {2026}, isbn = {978-2-493814-49-4}, language = {english}, url = {https://lrec.elra.info/lrec2026-main-820}, doi = {10.63317/38qenrwzegr9}, abstract = {Bangla Sign Language (BdSL) translation represents a low-resource NLP task due to the lack of large-scale datasets that address sentence-level translation. Correspondingly, existing research in this field has been limited to word and alphabet level detection. In this work, we introduce Bangla-SGP, a novel parallel dataset consisting of 1,000 human-annotated sentence--gloss pairs which was augmented with around 3,000 synthetically generated pairs using syntactic and morphological rules through a rule-based Retrieval-Augmented Generation (RAG) pipeline. The gloss sequences of the spoken Bangla sentences are made up of individual glosses which are Bangla sign supported words and serve as an intermediate representation for a continuous sign. Our dataset consists of 1000 high quality Bangla sentences that are manually annotated into a gloss sequence by a professional signer. The augmentation process incorporates rule-based linguistic strategies and prompt engineering techniques that we have adopted by critically analyzing our human annotated sentence-gloss pairs and by working closely with our professional signer. Furthermore, we fine-tune several transformer-based models such as mBart50, Google mT5, GPT4.1-nano and evaluate their sentence-to-gloss translation performance using BLEU scores, based on these evaluation metrics we compare the model's gloss-translation consistency across our dataset and the RWTH-PHOENIX-2014T benchmark.} } @inproceedings{phuangchoke-polprasert-2026-codebook:lrec, author = {Phuangchoke, Ninlawat and Polprasert, Chantri}, title = {Bridging Text-to-Sign Translation via Codebook-Oriented Pretraining}, pages = {9504--9513}, editor = {Piperidis, Stelios and Bel, N{\'u}ria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio}, booktitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {11--16}, month = may, year = {2026}, isbn = {978-2-493814-49-4}, language = {english}, url = {https://lrec.elra.info/lrec2026-main-746}, doi = {10.63317/2s9976y7ibcu}, abstract = {Sign Language Production (SLP), the automatic translation from spoken to sign languages, faces several challenges due to the intricate mapping between linguistic semantics and the spatial--temporal motion domain. Existing SLP methods employing a transformer model with a Vector Quantization (VQ) method exhibit poor translation performance due to weak semantic alignment between the codebook and the text representation. In this work, we propose a novel text-to-sign translation based on model pretraining, which enhances semantic alignment by inheriting codebook-oriented prior knowledge from masked self-supervised models. Our approach involves two stages: (i) transforming sign language into discrete values by employing VQ with masked self-attention learning to create pre-tasks that bridge the semantic gap between text and codebook representations, (ii) constructing an end-to-end architecture with an encoder-decoder-like structure that inherits the parameters of the model from the first stage. The integration of these designs forms a robust sign language representation and significantly improves the translation model, which surpass prior baselines.} } @inproceedings{inoue-etal-2026-continuity:lrec, author = {Inoue, Jundai and Hara, Daisuke and Miwa, Makoto}, title = {A Resource and Evaluation Method for Phonological Continuity in {Japanese} {Sign} {Language}}, pages = {9514--9524}, editor = {Piperidis, Stelios and Bel, N{\'u}ria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio}, booktitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {11--16}, month = may, year = {2026}, isbn = {978-2-493814-49-4}, language = {english}, url = {https://lrec.elra.info/lrec2026-main-747}, doi = {10.63317/4p22nojyxbxa}, abstract = {Computational models for sign language processing often represent phonological components as categories. This approach, however, does not adequately capture the continuous nature of sign articulation, obscuring nuanced phonetic variation. Furthermore, the field has lacked resources and standardized methods to evaluate a model's ability to represent this continuity. In this work, we address these limitations. First, we introduce the JSL Ordered Triplet Dataset, a new manually-annotated resource designed to benchmark the modeling of gradual phonological progressions in Japanese Sign Language. Second, we propose a learning framework that reframes the task from classification to ranking, using Positive-Unlabeled (PU) learning to optimize the Area Under the ROC Curve (AUC). Our intrinsic evaluation on the new dataset shows that the learned continuous embeddings significantly outperform a cross-entropy baseline in ordering intermediate forms, improving the average accuracy on the continuity ranking task across phonological components from 81.52{\%} to 91.71{\%}. These embeddings also maintain strong discriminative power for standard component classification. This work provides the community with a valuable resource and a method for learning and evaluating more linguistically-grounded representations of sign language.} } @inproceedings{nunnari-etal-2026-fairy:lrec, author = {Nunnari, Fabrizio and Jain, Siddhant and Gebhard, Patrick}, title = {Sentiment Analysis of {German} {Sign} {Language} Fairy Tales}, pages = {9525--9534}, editor = {Piperidis, Stelios and Bel, N{\'u}ria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio}, booktitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {11--16}, month = may, year = {2026}, isbn = {978-2-493814-49-4}, language = {english}, url = {https://lrec.elra.info/lrec2026-main-748}, doi = {10.63317/3cyfzw6vs9oe}, abstract = {We present a dataset and a model for sentiment analysis of German sign language (DGS) fairy tales. First, we perform sentiment analysis for three levels of valence (negative, neutral, positive) on German fairy tales text segments using four large language models (LLMs) and majority voting, reaching an inter-annotator agreement of 0.781 Krippendorff's alpha. Second, we extract face and body motion features from each corresponding DGS video segment using MediaPipe. Finally, we train an explainable model (based on XGBoost) to predict negative, neutral or positive sentiment from video features. Results show an average balanced accuracy of 0.631. A thorough analysis of the most important features reveal that, in addition to eyebrows and mouth motion on the face, also the motion of hips, elbows, and shoulders considerably contribute in the discrimination of the conveyed sentiment, indicating an equal importance of face and body for sentiment communication in sign language.} } @inproceedings{yazdani-etal-2026-critical:lrec, author = {Yazdani, Shakib and Hamidullah, Yasser and Espa{\~n}a-Bonet, Cristina and Avramidis, Eleftherios and van Genabith, Josef}, title = {A Critical Study of Automatic Evaluation in Sign Language Translation}, pages = {9535--9548}, editor = {Piperidis, Stelios and Bel, N{\'u}ria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio}, booktitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {11--16}, month = may, year = {2026}, isbn = {978-2-493814-49-4}, language = {english}, url = {https://lrec.elra.info/lrec2026-main-749}, doi = {10.63317/4n2sooe4fb2i}, abstract = {Automatic evaluation metrics are crucial for advancing sign language translation (SLT). Current SLT evaluation metrics, such as BLEU and ROUGE, are only text-based, and it remains unclear to what extent text-based metrics can reliably capture the quality of SLT outputs. To address this gap, we investigate the limitations of text-based SLT evaluation metrics by analyzing six metrics, including BLEU, chrF, and ROUGE, as well as BLEURT on the one hand, and large language model (LLM)-based evaluators such as G-Eval and GEMBA zero-shot direct assessment on the other hand. Specifically, we assess the consistency and robustness of these metrics under three controlled conditions: paraphrasing, hallucinations in model outputs, and variations in sentence length. Our analysis highlights the limitations of lexical overlap metrics and demonstrates that while LLM-based evaluators better capture semantic equivalence often missed by conventional metrics, they can also exhibit bias toward LLM-paraphrased translations. Moreover, although all metrics are able to detect hallucinations, BLEU tends to be overly sensitive, whereas BLEURT and LLM-based evaluators are comparatively lenient toward subtle cases. This motivates the need for multimodal evaluation frameworks that extend beyond text-based metrics to enable a more holistic assessment of SLT outputs.} } @inproceedings{kozhirbayev-imashev-2026-llm:lrec, author = {Kozhirbayev, Zhanibek and Imashev, Alfarabi}, title = {Evaluating Large Language Models for Text-to-Gloss Translation in {Kazakh-Russian} {Sign} {Language}: A Pilot Study}, pages = {9964--9972}, editor = {Piperidis, Stelios and Bel, N{\'u}ria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio}, booktitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {11--16}, month = may, year = {2026}, isbn = {978-2-493814-49-4}, language = {english}, url = {https://lrec.elra.info/lrec2026-main-781}, doi = {10.63317/2ikts3xaqget}, abstract = {Conceptual glossing involves a systematic linguistic transformation in which the models must preserve meaning, grammatical integrity, and punctuation while turning the real language into a more structured structure. The purpose of this study is to assess the accuracy and dependability of glosses produced by these models by juxtaposing them with human-annotated standards, investigating whether the models maintain essential linguistic characteristics. By identifying the strengths and weaknesses of each model, we want to determine which architectures are most suitable for organized language tasks, such as glossing. This may reduce the manual labor required for linguistic annotation by experts while maintaining superior quality outcomes. And help deaf signers with weak reading skills interpret written paragraphs into glosses, making them more comprehensible and naturally looking to them. Text-to-gloss translation converts written or spoken language into sign language glosses, enhancing accessibility for the Deaf and Hard of Hearing (DHH) community. This pilot study evaluates four large language models (LLMs): GPT-4-turbo, Grok 3, Deepseek-V3, and Gemini 20 Flash to generate conceptual glosses in Kazakh-Russian Sign Language (K-RSL), still an under-resourced sign language. Using a dataset of 250 Russian sentences with expert-annotated K-RSL glosses, we assess performance across METEOR, BLEU, BERTScore, and WER. Results show Deepseek-V3 excels on complex texts (METEOR: 0.426 for K-RSL word order, 0.377 for fairytale paragraphs), while Gemini 20 Flash performs strongly on short sentences (METEOR: 0.602). These findings demonstrate LLMs' potential to automate gloss production, reducing manual annotation and aiding DHH individuals with reading comprehension. Challenges include K-RSL's unique grammar and limited datasets. This is the first study to apply LLMs to K-RSL glossing and examine the potential efficacy of autonomous gloss production.} } @inproceedings{klezovich-etal-2026-enough:lrec, author = {Klezovich, Anna and Mesch, Johanna and Henter, Gustav Eje and Beskow, Jonas}, title = {How Much Data Is Enough Data? A New Motion Capture Corpus for Probabilistic Sign Language Generation}, pages = {9549--9558}, editor = {Piperidis, Stelios and Bel, N{\'u}ria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio}, booktitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {11--16}, month = may, year = {2026}, isbn = {978-2-493814-49-4}, language = {english}, url = {https://lrec.elra.info/lrec2026-main-750}, doi = {10.63317/5pmyrs7f9o33}, abstract = {We present a new 4.1 hours long high-quality motion capture sign language dataset for Swedish Sign Language --- STS Mocap v1. The dataset consists of high quality multimodal data: body tracked with markers, fingers tracked with Manus Quantum Metagloves, face tracked with iPhone LiveLink app in MetaHuman Animator mode, and corresponding textual sentence translation to spoken Swedish. With the help of this dataset, we show that four hours of motion capture data is enough for generative modeling of sign language conditioned on 2D pose. In comparison, training the same flow-matching model on only 30 minutes of this data, which is a common size for sign language motion capture datasets, shows a significant degradation in the quality of the synthesized data.} } @inproceedings{sevilla-lahozbengoechea-2026-multiband:lrec, author = {Sevilla, Antonio F. G. and Lahoz-Bengoechea, Jos{\'e} Mar{\'i}a}, title = {Decomposing Sign Language Movements: A Multi-Band Visualization Method for Articulatory Analysis}, pages = {9559--9568}, editor = {Piperidis, Stelios and Bel, N{\'u}ria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio}, booktitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {11--16}, month = may, year = {2026}, isbn = {978-2-493814-49-4}, language = {english}, url = {https://lrec.elra.info/lrec2026-main-751}, doi = {10.63317/32sdurbs4fio}, abstract = {Understanding the structure of sign language movements requires methods that can isolate and analyze the hierarchical and simultaneous nature of sign articulation. We present a method for tracking and visualizing sign language movements that progressively isolates dependent movements within the articulatory chain: hand rotation from arm displacement and finger movement from hand movement. Using MediaPipe hand tracking on ordinary 2D video, we decompose motion into separate gestural components and compute velocity and direction for each articulator. We present these movement channels in a time-aligned multi-band visualization that reveals temporal structure, bimanual synchronization patterns, and the coordination of different articulatory components. An interactive web-based viewer synchronizes the visualization with video, enabling researchers to efficiently explore movement patterns and their relationship to signing. We demonstrate the method with examples from isolated signs and continuous signing, showing how it reveals patterns that are difficult to observe in raw video, including bimanual coordination, internal movements, and the distinction between linguistic and non-linguistic segments. This approach provides accessible tools for empirical investigation of rhythmic and prosodic patterns in sign languages.} } @inproceedings{imai-etal-2026-shape:lrec, author = {Imai, Saki and Kezar, Lee and Aichler, Laurel and Inan, Mert and Walker, Erin and Wooten, Alicia and Quandt, Lorna Cobban and Alikhan, Malihe}, title = {How Pragmatics Shape Articulation: A Computational Case Study in {STEM} {ASL} Discourse}, pages = {8476--8490}, editor = {Piperidis, Stelios and Bel, N{\'u}ria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio}, booktitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {11--16}, month = may, year = {2026}, isbn = {978-2-493814-49-4}, language = {english}, url = {https://lrec.elra.info/lrec2026-main-669}, doi = {10.63317/2wjnaaabgz4d}, abstract = {Most state-of-the-art sign language models are trained on interpreter or isolated vocabulary data, which overlooks the variability that characterizes natural dialogue. However, human communication dynamically adapts to contexts and interlocutors through spatiotemporal changes and articulation style. This specifically manifests itself in educational settings, where novel vocabularies are used by teachers, and students. To address this gap, we collect a motion capture dataset of American Sign Language (ASL) STEM (Science, Technology, Engineering, and Mathematics) dialogue that enables quantitative comparison between dyadic interactive signing, solo signed lecture, and interpreted articles. Using continuous kinematic features, we disentangle dialogue-specific entrainment from individual effort reduction and show spatiotemporal changes across repeated mentions of STEM terms. On average, dialogue signs are 24.6{\%}-44.6{\%} shorter in duration than the isolated signs, and show significant reductions absent in monologue contexts. Finally, we evaluate sign embedding models on their ability to recognize STEM signs and approximate how entrained the participants become over time. Our study bridges linguistic analysis and computational modeling to understand how pragmatics shape sign articulation and its representation in sign language technologies.} } @inproceedings{vezzani-2026-terminology:lrec, author = {Vezzani, Federica}, title = {Representing Multimodality in Terminology Resources}, pages = {1320--1330}, editor = {Piperidis, Stelios and Bel, N{\'u}ria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio}, booktitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {11--16}, month = may, year = {2026}, isbn = {978-2-493814-49-4}, language = {english}, url = {https://lrec.elra.info/lrec2026-main-102}, doi = {10.63317/2n5q4sh59xp9}, abstract = {This paper addresses the lack of a multimodal approach to specialized knowledge representation in terminology work. In particular, we introduce a new Multimodal Terminological Metamodel (MTM) for the design of terminology resources which introduces an explicit modality layer, enabling uniform modelling of different language modalities within domain-specific and concept-oriented resources. The metamodel is formalised via an entity-relationship schema and a systematic contrast with the baseline framework -- the Terminological Markup Framework (TMF; ISO-16642 (2017)) -- to specify revised entities, relations, and cardinalities. As case study, we instantiate the MTM for the signed modality by defining a minimal data-category module with level-placement constraints, and we provide a lightweight, TBX-inspired XML serialisation that packages modality-specific terminological data in a consistent structure. Together, these components deliver a reproducible specification for designing and exchanging multimodal terminology resources.} } @inproceedings{barth-etal-2026-textplus:lrec, author = {Barth, Florian and Draxler, Christoph and Ecker, Jennifer and Fischer, Stefan and Gen{\^e}t, Philippe and Hemmer, Alina and Lehmberg, Timm and Trippel, Thorsten and Witt, Andreas and Zimmermann, Arden and Zinn, Claus}, title = {Text+: A National Hub Including Legacy Language Data}, pages = {8264--8275}, editor = {Piperidis, Stelios and Bel, N{\'u}ria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio}, booktitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)}, publisher = {{ELRA Language Resources Association (ELRA)}}, address = {Palma, Mallorca, Spain}, day = {11--16}, month = may, year = {2026}, isbn = {978-2-493814-49-4}, language = {english}, url = {https://lrec.elra.info/lrec2026-main-654}, doi = {10.63317/4vx5d59r6m29}, abstract = {Text+ is the German distributed research data infrastructure for literary studies, linguistics, and spoken and written language. Its resources consist of contemporary and historical literary and media texts, deeply annotated material, transcripts of spoken and sign language, and original recordings. Text+ provides access to its resources according to the FAIR guidelines: Findable due to standard-conformant metadata, Accessible with single sign-on authentication, Interoperable via open data formats, and Reproducible through web services and extensive documentation. The 30+ partners of Text+ are archives, libraries, universities, and other research institutions. The partners are autonomous, and they differ in the amount of data and processing capabilities they provide. In this paper, we describe the hub architecture of Text+, which gives users a central and FAIR point of access to research data that continues to be distributed across the Text+ partner institutions. The architecture serves as a blueprint to evolving research infrastructures that aim at maintaining (and empowering) their research data contributors.} } @inproceedings{hu-etal-2024-aggregation:lrec, author = {Hu, Lianyu and Gao, Liqing and Liu, Zekang and Feng, Du Wei}, title = {Dynamic Spatial-Temporal Aggregation for Skeleton-Aware Sign Language Recognition}, pages = {5450--5460}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.484}, doi = {10.63317/2sjtkug9vfy5}, abstract = {Skeleton-aware sign language recognition (SLR) has gained popularity due to its ability to remain unaffected by background information and its lower computational requirements. Current methods utilize spatial graph modules and temporal modules to capture spatial and temporal features, respectively. However, their spatial graph modules are typically built on fixed graph structures such as graph convolutional networks or a single learnable graph, which only partially explore joint relationships. Additionally, a simple temporal convolution kernel is used to capture temporal information, which may not fully capture the complex movement patterns of different signers. To overcome these limitations, we propose a new spatial architecture consisting of two concurrent branches, which build input-sensitive joint relationships and incorporates specific domain knowledge for recognition, respectively. These two branches are followed by an aggregation process to distinguishe important joint connections. We then propose a new temporal module to model multi-scale temporal information to capture complex human dynamics. Our method achieves state-of-the-art accuracy compared to previous skeleton-aware methods on four large-scale SLR benchmarks. Moreover, our method demonstrates superior accuracy compared to RGB-based methods in most cases while requiring much fewer computational resources, bringing better accuracy-computation trade-off. Code is available at https://github.com/hulianyuyy/DSTA-SLR.} } @inproceedings{chen-etal-2024-factorized:lrec, author = {Chen, Zhigang and Zhou, Benjia and Li, Jun and Wan, Jun and Lei, Zhen and Jiang, Ning and Lu, Quan and Zhao, Guoqing}, title = {Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation}, pages = {7071--7081}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.620}, doi = {10.63317/4qo2dsetvyk8}, abstract = {Previous Sign Language Translation (SLT) methods achieve superior performance by relying on gloss annotations. However, labeling high-quality glosses is a labor-intensive task, which limits the further development of SLT. Although some approaches work towards gloss-free SLT through jointly training the visual encoder and translation network, these efforts still suffer from poor performance and inefficient use of the powerful Large Language Model (LLM). Most seriously, we find that directly introducing LLM into SLT will lead to insufficient learning of visual representations as LLM dominates the learning curve. To address these problems, we propose Factorized Learning assisted with Large Language Model (FLa-LLM) for gloss-free SLT. Concretely, we factorize the training process into two stages. In the visual initialing stage, we employ a lightweight translation model after the visual encoder to pre-train the visual encoder. In the LLM fine-tuning stage, we freeze the acquired knowledge in the visual encoder and integrate it with a pre-trained LLM to inspire the LLM's translation potential. This factorized training strategy proves to be highly effective as evidenced by significant improvements achieved across three SLT datasets which are all conducted under the gloss-free setting.} } @inproceedings{kim-etal-2024-safety:lrec, author = {Kim, Wooyoung and Kim, Taeyong and Kim, Byeongjin and Lee, Myeongjin and Lee, Gitaek and Kim, Kirok and Cha, Jisoo and Kim, Wooju}, title = {{SSL}: {Korean} Disaster Safety Information Sign Language Translation Benchmark Dataset}, pages = {9948--9953}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.869}, doi = {10.63317/563mhir2b5cd}, abstract = {Sign language is a crucial means of communication for deaf communities. However, those outside deaf communities often lack understanding of sign language, leading to inadequate communication accessibility for the deaf. Therefore, sign language translation is a significantly important research area. In this context, we present a new benchmark dataset for Korean sign language translation named SSL:korean disaster Safety information Sign Language translation benchmark dataset. Korean sign language translation datasets provided by the National Information Society Agency in South Korea have faced challenges related to computational resources, heterogeneity between train and test sets, and unrefined data. To alleviate the aforementioned issue, we refine the origin data and release them. Additionally, we report experimental results of baseline using a transformer architecture. We empirically demonstrate that the baseline performance varies depending on the tokenization method applied to gloss sequences. In particular, tokenization based on characteristics of sign language outperforms tokenization considering characteristics of spoken language and tokenization utilizing statistical techniques. We release materials at our https://github.com/SSL-Sign-Language/Korean-Disaster-Safety-Information-Sign-Language-Translation-Benchmark-Dataset} } @inproceedings{krebs-etal-2024-motion:lrec, author = {Krebs, Julia and Malaia, Evie A. and Fessl, Isabella and Wiesinger, Hans-Peter and Roehm, Dietmar and Wilbur, Ronnie and Schwameder, Hermann}, title = {Motion Capture Analysis of Verb and Adjective Types in {Austrian} {Sign} {Language} ({{\"O}GS})}, pages = {11619--11624}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.1015}, doi = {10.63317/5g2za8h2gtjq}, abstract = {Across a number of sign languages, temporal and spatial characteristics of dominant hand articulation are used to express semantic and grammatical features. In this study of Austrian Sign Language ({\"O}sterreichische Geb{\"a}rdensprache, or {\"O}GS), motion capture data of four Deaf signers is used to quantitatively characterize the kinematic parameters of sign production in verbs and adjectives. We investigate (1) the difference in production between verbs involving a natural endpoint (telic verbs; e.g. arrive) and verbs lacking an endpoint (atelic verbs; e.g. analyze), and (2) adjective signs in intensified vs. non-intensified (plain) forms. Motion capture data analysis using linear-mixed effects models (LME) indicates that both the endpoint marking in verbs, as well as marking of intensification in adjectives, are expressed by movement modulation in {\"O}GS. While the semantic distinction between verb types (telic/atelic) is marked by higher peak velocity and shorter duration for telic signs compared to atelic ones, the grammatical distinction (intensification) in adjectives is expressed by longer duration for intensified compared to non-intensified adjectives. The observed individual differences of signers might be interpreted as personal signing style.} } @inproceedings{walsh-etal-2024-select:lrec, author = {Walsh, Harry and Saunders, Ben and Bowden, Richard}, title = {Select and Reorder: A Novel Approach for Neural Sign Language Production}, pages = {14531--14542}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.1266}, doi = {10.63317/362tbumoxwha}, abstract = {Sign languages, often categorised as low-resource languages, face significant challenges in achieving accurate translation due to the scarcity of parallel annotated datasets. This paper introduces Select and Reorder (S{\&}R), a novel approach that addresses data scarcity by breaking down the translation process into two distinct steps: Gloss Selection (GS) and Gloss Reordering (GR). Our method leverages large spoken language models and the substantial lexical overlap between source spoken languages and target sign languages to establish an initial alignment. Both steps make use of Non-AutoRegressive (NAR) decoding for reduced computation and faster inference speeds. Through this disentanglement of tasks, we achieve state-of-the-art BLEU and Rouge scores on the Meine DGS Annotated (mDGS) dataset, demonstrating a substantial BLUE-1 improvement of 37.88{\%} in Text to Gloss (T2G) Translation. This innovative approach paves the way for more effective translation models for sign languages, even in resource-constrained settings.} } @inproceedings{kim-etal-2024-signbleu:lrec, author = {Kim, Jung-Ho and Huerta-Enochian, Mathew and Ko, Changyong and Lee, Du Hui}, title = {{SignBLEU}: Automatic Evaluation of Multi-channel Sign Language Translation}, pages = {14796--14811}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.1289}, doi = {10.63317/2zet3x846x3m}, abstract = {Sign languages are multi-channel languages that communicate information through not just the hands (manual signals) but also facial expressions and upper body movements (non-manual signals). However, since automatic sign language translation is usually performed by generating a single sequence of glosses, researchers eschew non-manual and co-occurring manual signals in favor of a simplified list of manual glosses. This can lead to significant information loss and ambiguity. In this paper, we introduce a new task named multi-channel sign language translation (MCSLT) and present a novel metric, SignBLEU, designed to capture multiple signal channels. We validated SignBLEU on a system-level task using three sign language corpora with varied linguistic structures and transcription methodologies and examined its correlation with human judgment through two segment-level tasks. We found that SignBLEU consistently correlates better with human judgment than competing metrics. To facilitate further MCSLT research, we report benchmark scores for the three sign language corpora and release the source code for SignBLEU at https://github.com/eq4all-projects/SignBLEU.} } @inproceedings{imashev-etal-2024-comparative:lrec, author = {Imashev, Alfarabi and Oralbayeva, Nurziya and Baizhanova, Gulmira and Sandygulova, Anara}, title = {Comparative Analysis of Sign Language Interpreting Agents Perception: A Study of the Deaf}, pages = {3603--3609}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.319}, doi = {10.63317/2ifmxciyene8}, abstract = {Prior research on sign language recognition has already demonstrated encouraging outcomes in achieving highly accurate and dependable automatic sign language recognition. The use of virtual characters as virtual assistants has significantly increased in the past decade. However, the progress in sign language generation and output that closely resembles physiologically believable human motions is still in its early stages. This assertion explains the lack of progress in virtual intelligent signing generative systems. Aside from the development of signing systems, scholarly research have revealed a significant deficiency in evaluating sign language generation systems by those who are deaf and use sign language. This paper presents the findings of a user study conducted with deaf signers. The study is aimed at comparing a state-of-the-art sign language generation system with a skilled sign language interpreter. The study focused on testing established metrics to gain insights into usability of such metrics for deaf signers and how deaf signers perceive signing agents.} } @inproceedings{huamani-malca-etal-2024-lessons:lrec, author = {Huamani-Malca, Joe and Rodr{\'i}guez Mondo{\~n}edo, Miguel and Cerna-Herrera, Francisco and Bejarano, Gissella and V{\'a}squez Roque, Carlos and Ramos Cantu, Cesar Augusto and Oporto P{\'e}rez, Sabina}, title = {Lessons from Deploying the First Bilingual {Peruvian} {Sign} {Language} - {Spanish} Online Dictionary}, pages = {10316--10323}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.901}, doi = {10.63317/3wjb6cvq8x2n}, abstract = {Bilingual dictionaries present several challenges, especially for sign languages and oral languages, where multimodality plays a role. We deployed and tested the first bilingual Peruvian Sign Language (LSP) - Spanish Online Dictionary. The first feature allows the user to introduce a text and receive as a result a list of videos whose glosses are related to the input text or Spanish word. The second feature allows the user to sign in front of the camera and shows the five most probable Spanish translations based on the similarity between the input sign and gloss-labeled sign videos used to train a machine learning model. These features are constructed in a design and architecture that differentiates among the coincidence for the Spanish text searched, the sign gloss, and Spanish translation. We explain in depth how these concepts or database columns impact the search. Similarly, we share the challenges of deploying a real-world machine learning model for isolated sign language recognition through Amazon Web Services (AWS).} } @inproceedings{ma-etal-2024-multichannel:lrec, author = {Ma, Xiaohan and Jin, Rize and Chung, Tae-Sun}, title = {Multi-Channel Spatio-Temporal Transformer for Sign Language Production}, pages = {11699--11712}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.1022}, doi = {10.63317/4b2rkf4368ih}, abstract = {The task of Sign Language Production (SLP) in machine learning involves converting text-based spoken language into corresponding sign language expressions. Sign language conveys meaning through the continuous movement of multiple articulators, including manual and non-manual channels. However, most current Transformer-based SLP models convert these multi-channel sign poses into a unified feature representation, ignoring the inherent structural correlations between channels. This paper introduces a novel approach called MCST-Transformer for skeletal sign language production. It employs multi-channel spatial attention to capture correlations across various channels within each frame, and temporal attention to learn sequential dependencies for each channel over time. Additionally, the paper explores and experiments with multiple fusion techniques to combine the spatial and temporal representations into naturalistic sign sequences. To validate the effectiveness of the proposed MCST-Transformer model and its constituent components, extensive experiments were conducted on two benchmark sign language datasets from diverse cultures. The results demonstrate that this new approach outperforms state-of-the-art models on both datasets.} } @inproceedings{nunnari-etal-2024-fabeln:lrec, author = {Nunnari, Fabrizio and Avramidis, Eleftherios and Espa{\~n}a-Bonet, Cristina and Gonz{\'a}lez, Marco and Hennes, Anna and Gebhard, Patrick}, title = {{DGS-Fabeln-1}: A Multi-Angle Parallel Corpus of Fairy Tales between {German} {Sign} {Language} and {German} Text}, pages = {4847--4857}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.434}, doi = {10.63317/46w4kw3gmw3v}, abstract = {We present the acquisition process and the data of DGS-Fabeln-1, a parallel corpus of German text and videos containing German fairy tales interpreted into the German Sign Language (DGS) by a native DGS signer. The corpus contains 573 segments of videos with a total duration of 1 hour and 32 minutes, corresponding with 1428 written sentences. It is the first corpus of semi-naturally expressed DGS that has been filmed from 7 angles, and one of the few sign language (SL) corpora globally which have been filmed from more than 3 angles and where the listener has been simultaneously filmed. The corpus aims at aiding research at SL linguistics, SL machine translation and affective computing, and is freely available for research purposes at the following address: https://doi.org/10.5281/zenodo.10822097.} } @inproceedings{challant-filhol-2024-nonmanual:lrec, author = {Challant, Camille and Filhol, Michael}, title = {Extending {AZee} with Non-manual Gesture Rules for {French} {Sign} {Language}}, pages = {7007--7016}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.614}, doi = {10.63317/572ko5qzgpka}, abstract = {This paper presents a study on non-manual gestures, using a formal model named AZee. This is an approach which allows to formally represent Sign Language (SL) discourses, but also to animate them with a virtual signer. As non-manual gestures are essential in SL and therefore necessary for a quality synthesis, we wanted to extend AZee with them, by adding some production rules to the AZee production set. For this purpose, we applied a methodology which allows to find new production rules on a corpus representing one hour of French Sign Language, the 40 br{\`e}ves (Challant and Filhol, 2022). 23 production rules for non-manual gestures in LSF have thus been determined. We took advantage of this study to directly insert these new rules in the first corpus of AZee discourses expressions, which describe with AZee the productions in SL of the 40 br{\`e}ves corpus. 533 non-manual rules were inserted in the corpus, and some updates were made. This article proposes a new version of this AZee expressions corpus.} } @inproceedings{jiang-etal-2024-swisssli:lrec, author = {Jiang, Zifan and G{\"o}hring, Anne and Moryossef, Amit and Sennrich, Rico and Ebling, Sarah}, title = {{SwissSLi}: the Multi-parallel Sign Language Corpus for {Switzerland}}, pages = {15448--15456}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.1342}, doi = {10.63317/2ptokbmctz25}, abstract = {In this work, we introduce SwissSLi, the first sign language corpus that contains parallel data of all three Swiss sign languages, namely Swiss German Sign Language (DSGS), French Sign Language of Switzerland (LSF-CH), and Italian Sign Language of Switzerland (LIS-CH). The data underlying this corpus originates from television programs in three spoken languages: German, French, and Italian. The programs have for the most part been translated into sign language by deaf translators, resulting in a unique, up to six-way multi-parallel dataset between spoken and sign languages. We describe and release the sign language videos and spoken language subtitles as well as the overall statistics and some derivatives of the raw material. These derived components include cropped videos, pose estimation, phrase/sign-segmented videos, and sentence-segmented subtitles, all of which facilitate downstream tasks such as sign language transcription (glossing) and machine translation. The corpus is publicly available on the SWISSUbase data platform for research purposes only under a CC BY-NC-SA 4.0 license.} } @inproceedings{sevilla-etal-2024-prosodic:lrec, author = {Sevilla, Antonio F. G. and Lahoz-Bengoechea, Jos{\'e} Mar{\'i}a and D{\'i}az Esteban, Alberto}, title = {Automated Extraction of Prosodic Structure from Unannotated Sign Language Video}, pages = {1808--1816}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.161}, doi = {10.63317/5etpjhtrjt9u}, abstract = {As in oral phonology, prosody is an important carrier of linguistic information in sign languages. One of the most prominent ways this reveals itself is in the time structure of signs: their rhythm and intensity of articulation. To be able to empirically see these effects, the velocity of the hands can be computed throughout the execution of a sign. In this article, we propose a method for extracting this information from unlabeled videos of sign language, exploiting CoTracker, a recent advancement in computer vision which can track every point in a video without the need of any calibration or fine-tuning. The dominant hand is identified via clustering of the computed point velocities, and its dynamic profile plotted to make apparent the prosodic structure of signing. We apply our method to different datasets and sign languages, and perform a preliminary visual exploration of results. This exploration supports the usefulness of our methodology for linguistic analysis, though issues to be tackled remain, such as bi-manual signs and a formal and numerical evaluation of accuracy. Nonetheless, the absence of any preprocessing requirements may make it useful for other researchers and datasets.} } @inproceedings{holmes-etal-2024-keypoints:lrec, author = {Holmes, Ruth and Rushe, Ellen and Ventresque, Anthony}, title = {The Key Points: Using Feature Importance to Identify Shortcomings in Sign Language Recognition Models}, pages = {15970--15975}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.1387}, doi = {10.63317/2edv5wfy7f5j}, abstract = {Pose estimation keypoints are widely used in sign language recognition (SLR) as a means of generalising to unseen signers. Despite the advantages of keypoints, SLR models struggle to achieve high recognition accuracy for many signed languages due to the large degree of variability between occurrences of the same signs, the lack of large datasets and the imbalanced nature of the data therein. In this paper we seek to provide a deeper analysis into the ways that these keypoints are used by models in order to determine which are most informative to SLR, identify potentially redundant ones and investigate whether keypoints that are central to differentiating signs in practice are being effectively used as expected by models.} } @inproceedings{niu-etal-2024-hksl:lrec, author = {Niu, Zhe and Zuo, Ronglai and Mak, Brian and Wei, Fangyun}, title = {A {Hong} {Kong} {Sign} {Language} Corpus Collected from Sign-interpreted {TV} News}, pages = {636--646}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.55}, doi = {10.63317/5g7ror2hcus7}, abstract = {This paper introduces TVB-HKSL-News, a new Hong Kong sign language (HKSL) dataset collected from a TV news program over a period of 7 months. The dataset is collected to enrich resources for HKSL and support research in large-vocabulary continuous sign language recognition (SLR) and translation (SLT). It consists of 16.07 hours of sign videos of two signers with a vocabulary of 6,515 glosses (for SLR) and 2,850 Chinese characters or 18K Chinese words (for SLT). One signer has 11.66 hours of sign videos and the other has 4.41 hours. One objective in building the dataset is to support the investigation of how well large-vocabulary continuous sign language recognition/translation can be done for a single signer given a (relatively) large amount of his/her training data, which could potentially lead to the development of new modeling methods. Besides, most parts of the data collection pipeline are automated with little human intervention; we believe that our collection method can be scaled up to collect more sign language data easily for SLT in the future for any sign languages if such sign-interpreted videos are available. We also run a SOTA SLR/SLT model on the dataset and get a baseline SLR word error rate of 34.08{\%} and a baseline SLT BLEU-4 score of 23.58 for benchmarking future research on the dataset.} } @inproceedings{xu-etal-2024-wwcsl:lrec, author = {Xu, Fan and Liu, Kai and Yang, Yifeng and Yan, Keyu}, title = {{WW-CSL}: A New Dataset for Word-Based Wearable {Chinese} {Sign} {Language} Detection}, pages = {17718--17724}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.1541}, doi = {10.63317/2j44679jy8ip}, abstract = {Sign language is an effective non-verbal communication mode for the hearing-impaired people. Since the video-based sign language detection models have high requirements for enough lighting and clear background, current wearing glove-based sign language models are robust for poor light and occlusion situations. In this paper, we annotate a new dataset of Word-based Wearable Chinese Sign Languag (WW-CSL) gestures. Specifically, we propose a three-form (e.g., sequential sensor data, gesture video, and gesture text) scheme to represent dynamic CSL gestures. Guided by the scheme, a total of 3,000 samples were collected, corresponding to 100 word-based CSL gestures. Furthermore, we present a transformer-based baseline model to fuse 2 inertial measurement unites (IMUs) and 10 flex sensors for the wearable CSL detection. In order to integrate the advantage of video-based and wearable glove-based CSL gestures, we also propose a transformer-based Multi-Modal CSL Detection (MM-CSLD) framework which adeptly integrates the local sequential sensor data derived from wearable-based CSL gestures with the global, fine-grained skeleton representations captured from video-based CSL gestures simultaneously.} } @inproceedings{sun-etal-2024-adaptive:lrec, author = {Sun, Tong and Fu, Biao and Hu, Cong and Zhang, Liang and Zhang, Ruiquan and Shi, Xiaodong and Su, Jinsong and Chen, Yidong}, title = {Adaptive Simultaneous Sign Language Translation with Confident Translation Length Estimation}, pages = {372--384}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)}, publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}}, address = {Torino, Italy}, day = {20--25}, month = may, year = {2024}, isbn = {978-2-493814-10-4}, language = {english}, url = {https://aclanthology.org/2024.lrec-main.34}, doi = {10.63317/3gk74qgqo8pn}, abstract = {Traditional non-simultaneous Sign Language Translation (SLT) methods, while effective for pre-recorded videos, face challenges in real-time scenarios due to inherent inference delays. The emerging field of simultaneous SLT aims to address this issue by progressively translating incrementally received sign video. However, the sole existing work in simultaneous SLT adopts a fixed gloss-based policy, which suffer from limitations in boundary prediction and contextual comprehension. In this paper, we delve deeper into this area and propose an adaptive policy for simultaneous SLT. Our approach introduces the concept of ``confident translation length'', denoting maximum accurate translation achievable from current input. An estimator measures this length for streaming sign video, enabling the model to make informed decisions on whether to wait for more input or proceed with translation. To train the estimator, we construct a training data of confident translation length based on the longest common prefix between translations of partial and complete inputs. Furthermore, we incorporate adaptive training, utilizing pseudo prefix pairs, to refine the offline translation model for optimal performance in simultaneous scenarios. Experimental results on PHOENIX2014T and CSL-Daily demonstrate the superiority of our adaptive policy over existing methods, particularly excelling in situations requiring extremely low latency.} } @inproceedings{kim-etal-2022-layering:lrec, author = {Kim, Jung-Ho and Hwang, Eui Jun and Cho, Sukmin and Lee, Du Hui and Park, Jong C.}, title = {Sign Language Production With Avatar Layering: A Critical Use Case over Rare Words}, pages = {1519--1528}, editor = {Calzolari, Nicoletta and B{\'e}chet, Fr{\'e}d{\'e}ric and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Odijk, Jan and Piperidis, Stelios}, booktitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {20--25}, month = jun, year = {2022}, isbn = {979-10-95546-72-6}, language = {english}, url = {https://aclanthology.org/2022.lrec-1.163}, doi = {10.63317/49nwsyfwve7m}, abstract = {Sign language production (SLP) is the process of generating sign language videos from spoken language expressions. Since sign languages are highly under-resourced, existing vision-based SLP approaches suffer from out-of-vocabulary (OOV) and test-time generalization problems and thus generate low-quality translations. To address these problems, we introduce an avatar-based SLP system composed of a sign language translation (SLT) model and an avatar animation generation module. Our Transformer-based SLT model utilizes two additional strategies to resolve these problems: named entity transformation to reduce OOV tokens and context vector generation using a pretrained language model (e.g., BERT) to reliably train the decoder. Our system is validated on a new Korean-Korean Sign Language (KSL) dataset of weather forecasts and emergency announcements. Our SLT model achieves an 8.77 higher BLEU-4 score and a 4.57 higher ROUGE-L score over those of our baseline model. In a user evaluation, 93.48{\%} of named entities were successfully identified by participants, demonstrating marked improvement on OOV issues.} } @inproceedings{declerck-2022-ontology:lrec, author = {Declerck, Thierry}, title = {Towards a new Ontology for Sign Languages}, pages = {3977--3983}, editor = {Calzolari, Nicoletta and B{\'e}chet, Fr{\'e}d{\'e}ric and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Odijk, Jan and Piperidis, Stelios}, booktitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {20--25}, month = jun, year = {2022}, isbn = {979-10-95546-72-6}, language = {english}, url = {https://aclanthology.org/2022.lrec-1.423}, doi = {10.63317/4grdn4cwm5br}, abstract = {We present the current status of a new ontology for representing constitutive elements of Sign Languages (SL). This development emerged from investigations on how to represent multimodal lexical data in the OntoLex-Lemon framework, with the goal to publish such data in the Linguistic Linked Open Data (LLOD) cloud. While studying the literature and various sites dealing with sign languages, we saw the need to harmonise all the data categories (or features) defined and used in those sources, and to organise them in an ontology to which lexical descriptions in OntoLex-Lemon could be linked. We make the code of the first version of this ontology available, so that it can be further developed collaboratively by both the Linked Data and the SL communities} } @inproceedings{jang-etal-2022-augmentation:lrec, author = {Jang, Jin Yea and Park, Han-Mu and Shin, Saim and Shin, Suna and Yoon, Byungcheon and Gweon, Gahgene}, title = {Automatic Gloss-level Data Augmentation for Sign Language Translation}, pages = {6808--6813}, editor = {Calzolari, Nicoletta and B{\'e}chet, Fr{\'e}d{\'e}ric and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Odijk, Jan and Piperidis, Stelios}, booktitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {20--25}, month = jun, year = {2022}, isbn = {979-10-95546-72-6}, language = {english}, url = {https://aclanthology.org/2022.lrec-1.734}, doi = {10.63317/29awmt3pbbjy}, abstract = {Securing sufficient data to enable automatic sign language translation modeling is challenging. The data insufficiency issue exists in both video and text modalities; however, fewer studies have been performed on text data augmentation compared to video data. In this study, we present three methods of augmenting sign language text modality data, comprising 3,052 Gloss-level Korean Sign Language (GKSL) and Word-level Korean Language (WKL) sentence pairs. Using each of the three methods, the following number of sentence pairs were created: blank replacement 10,654, sentence paraphrasing 1,494, and synonym replacement 899. Translation experiment results using the augmented data showed that when translating from GKSL to WKL and from WKL to GKSL, Bi-Lingual Evaluation Understudy (BLEU) scores improved by 0.204 and 0.170 respectively, compared to when only the original data was used. The three contributions of this study are as follows. First, we demonstrated that three different augmentation techniques used in existing Natural Language Processing (NLP) can be applied to sign language. Second, we propose an automatic data augmentation method which generates quality data by utilizing the Korean sign language gloss dictionary. Lastly, we publish the Gloss-level Korean Sign Language 13k dataset (GKSL13k), which has verified data quality through expert reviews.} } @inproceedings{dafnis-etal-2022-bidirectional:lrec, author = {Dafnis, Konstantinos M. and Chroni, Evgenia and Neidle, Carol and Metaxas, Dimitris}, title = {Bidirectional Skeleton-Based Isolated Sign Recognition using Graph Convolutional Networks}, pages = {7328--7338}, editor = {Calzolari, Nicoletta and B{\'e}chet, Fr{\'e}d{\'e}ric and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Odijk, Jan and Piperidis, Stelios}, booktitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {20--25}, month = jun, year = {2022}, isbn = {979-10-95546-72-6}, language = {english}, url = {https://aclanthology.org/2022.lrec-1.797}, doi = {10.63317/2pkthubupe7n}, abstract = {To improve computer-based recognition from video of isolated signs from American Sign Language (ASL), we propose a new skeleton-based method that involves explicit detection of the start and end frames of signs, trained on the ASLLVD dataset; it uses linguistically relevant parameters based on the skeleton input. Our method employs a bidirectional learning approach within a Graph Convolutional Network (GCN) framework. We apply this method to the WLASL dataset, but with corrections to the gloss labeling to ensure consistency in the labels assigned to different signs; it is important to have a 1-1 correspondence between signs and text-based gloss labels. We achieve a success rate of 77.43{\%} for top-1 and 94.54{\%} for top-5 using this modified WLASL dataset. Our method, which does not require multi-modal data input, outperforms other state-of-the-art approaches on the same modified WLASL dataset, demonstrating the importance of both attention to the start and end frames of signs and the use of bidirectional data streams in the GCNs for isolated sign recognition.} } @inproceedings{challant-filhol-2022-corpus:lrec, author = {Challant, Camille and Filhol, Michael}, title = {A First Corpus of {AZee} Discourse Expressions}, pages = {1560--1565}, editor = {Calzolari, Nicoletta and B{\'e}chet, Fr{\'e}d{\'e}ric and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Odijk, Jan and Piperidis, Stelios}, booktitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {20--25}, month = jun, year = {2022}, isbn = {979-10-95546-72-6}, language = {english}, url = {https://aclanthology.org/2022.lrec-1.167}, doi = {10.63317/3iu6ksnfvxk6}, abstract = {This paper presents a corpus of AZee discourse expressions, i.e. expressions which formally describe Sign Language utterances of any length using the AZee approach and language. The construction of this corpus had two main goals: a first reference corpus for AZee, and a test of its coverage on a significant sample of real-life utterances. We worked on productions from an existing corpus, namely the "40 breves", containing an hour of French Sign Language. We wrote the corresponding AZee discourse expressions for the entire video content, i.e. expressions capturing the forms produced by the signers and their associated meaning by combining known production rules, a basic building block for these expressions. These are made available as a version 2 extension of the "40 breves". We explain the way in which these expressions can be built, present the resulting corpus and set of production rules used, and perform first measurements on it. We also propose an evaluation of our corpus: for one hour of discourse, AZee allows to describe 94{\%} of it, while ongoing studies are increasing this coverage. This corpus offers a lot of future prospects, for instance concerning synthesis with virtual signers, machine translation or formal grammars for Sign Language.} } @inproceedings{sisto-etal-2022-challenges:lrec, author = {De Sisto, Mirella and Vandeghinste, Vincent and Egea G{\'o}mez, Santiago and De Coster, Mathieu and Shterionov, Dimitar}, title = {Challenges with Sign Language Datasets for Sign Language Recognition and Translation}, pages = {2478--2487}, editor = {Calzolari, Nicoletta and B{\'e}chet, Fr{\'e}d{\'e}ric and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Odijk, Jan and Piperidis, Stelios}, booktitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {20--25}, month = jun, year = {2022}, isbn = {979-10-95546-72-6}, language = {english}, url = {https://aclanthology.org/2022.lrec-1.264}, doi = {10.63317/4naj43uhhdys}, abstract = {Sign Languages (SLs) are the primary means of communication for at least half a million people in Europe alone. However, the development of SL recognition and translation tools is slowed down by a series of obstacles concerning resource scarcity and standardization issues in the available data. The former challenge relates to the volume of data available for machine learning as well as the time required to collect and process new data. The latter obstacle is linked to the variety of the data, i.e., annotation formats are not unified and vary amongst different resources. The available data formats are often not suitable for machine learning, obstructing the provision of automatic tools based on neural models. In the present paper, we give an overview of these challenges by comparing various SL corpora and SL machine learning datasets. Furthermore, we propose a framework to address the lack of standardization at format level, unify the available resources and facilitate SL research for different languages. Our framework takes ELAN files as inputs and returns textual and visual data ready to train SL recognition and translation models. We present a proof of concept, training neural translation models on the data produced by the proposed framework.} } @inproceedings{mertz-etal-2022-motion:lrec, author = {Mertz, Cl{\'e}mence and Barreaud, Vincent and Le Naour, Thibaut and Lolive, Damien and Gibet, Sylvie}, title = {A Low-Cost Motion Capture Corpus in {French} {Sign} {Language} for Interpreting Iconicity and Spatial Referencing Mechanisms}, pages = {2488--2497}, editor = {Calzolari, Nicoletta and B{\'e}chet, Fr{\'e}d{\'e}ric and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Odijk, Jan and Piperidis, Stelios}, booktitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {20--25}, month = jun, year = {2022}, isbn = {979-10-95546-72-6}, language = {english}, url = {https://aclanthology.org/2022.lrec-1.265}, doi = {10.63317/3czcts98xw8d}, abstract = {The automatic translation of sign language videos into transcribed texts is rarely approached in its whole, as it implies to finely model the grammatical mechanisms that govern these languages. The presented work is a first step towards the interpretation of French sign language (LSF) by specifically targeting iconicity and spatial referencing. This paper describes the LSF-SHELVES corpus as well as the original technology that was designed and implemented to collect it. Our goal is to use deep learning methods to circumvent the use of models in spatial referencing recognition. In order to obtain training material with sufficient variability, we designed a light-weight (and low-cost) capture protocol that enabled us to collect data from a large panel of LSF signers. This protocol involves the use of a portable device providing a 3D skeleton, and of a software developed specifically for this application to facilitate the post-processing of handshapes. The LSF-SHELVES includes simple and compound iconic and spatial dynamics, organized in 6 complexity levels, representing a total of 60 sequences signed by 15 LSF signers.} } @inproceedings{schulder-hanke-2022-fair:lrec, author = {Schulder, Marc and Hanke, Thomas}, title = {How to be {FAIR} when you {CARE}: The {DGS} {Corpus} as a Case Study of Open Science Resources for Minority Languages}, pages = {164--173}, editor = {Calzolari, Nicoletta and B{\'e}chet, Fr{\'e}d{\'e}ric and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Odijk, Jan and Piperidis, Stelios}, booktitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {20--25}, month = jun, year = {2022}, isbn = {979-10-95546-72-6}, language = {english}, url = {https://aclanthology.org/2022.lrec-1.18}, doi = {10.63317/3meqtpjx83oj}, abstract = {The publication of resources for minority languages requires a balance between making data open and accessible and respecting the rights and needs of its language community. The FAIR principles were introduced as a guide to good open data practices and they have since been complemented by the CARE principles for indigenous data governance. This article describes how the DGS Corpus implemented these principles and how the two sets of principles affected each other. The DGS Corpus is a large collection of recordings of members of the deaf community in Germany communicating in their primary language, German Sign Language (DGS); it was created to be both as a resource for linguistic research and as a record of the life experiences of deaf people in Germany. The corpus was designed with CARE in mind to respect and empower the language community and FAIR data publishing was used to enhance its usefulness as a scientific resource.} } @inproceedings{bertinlemee-etal-2022-rosettalsf:lrec, author = {Bertin-Lem{\'e}e, Elise and Braffort, Annelies and Challant, Camille and Danet, Claire and Dauriac, Boris and Filhol, Michael and Martinod, Emmanuella and Segouat, J{\'e}r{\'e}mie}, title = {{Rosetta-LSF}: an Aligned Corpus of {French} {Sign} {Language} and {French} for Text-to-Sign Translation}, pages = {4955--4962}, editor = {Calzolari, Nicoletta and B{\'e}chet, Fr{\'e}d{\'e}ric and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Odijk, Jan and Piperidis, Stelios}, booktitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {20--25}, month = jun, year = {2022}, isbn = {979-10-95546-72-6}, language = {english}, url = {https://aclanthology.org/2022.lrec-1.529}, doi = {10.63317/28x9znhmna2p}, abstract = {This article presents a new French Sign Language (LSF) corpus called "Rosetta-LSF". It was created to support future studies on the automatic translation of written French into LSF, rendered through the animation of a virtual signer. An overview of the field highlights the importance of a quality representation of LSF. In order to obtain quality animations understandable by signers, it must surpass the simple "gloss transcription" of the LSF lexical units to use in the discourse. To achieve this, we designed a corpus composed of four types of aligned data, and evaluated its usability. These are: news headlines in French, translations of these headlines into LSF in the form of videos showing animations of a virtual signer, gloss annotations of the "traditional" type---although including additional information on the context in which each gestural unit is performed as well as their potential for adaptation to another context---and AZee representations of the videos, i.e. formal expressions capturing the necessary and sufficient linguistic information. This article describes this data, exhibiting an example from the corpus. It is available online for public research.} } @inproceedings{sevilla-etal-2022-quevedo:lrec, author = {Sevilla, Antonio F. G. and D{\'i}az Esteban, Alberto and Lahoz-Begoechea, Jos{\'e} Mar{\'i}a}, title = {{Quevedo}: Annotation and Processing of Graphical Languages}, pages = {2528--2535}, editor = {Calzolari, Nicoletta and B{\'e}chet, Fr{\'e}d{\'e}ric and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Odijk, Jan and Piperidis, Stelios}, booktitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {20--25}, month = jun, year = {2022}, isbn = {979-10-95546-72-6}, language = {english}, url = {https://aclanthology.org/2022.lrec-1.269}, doi = {10.63317/3o5k57ihtc7d}, abstract = {In this article, we present Quevedo, a software tool we have developed for the task of automatic processing of graphical languages. These are languages which use images to convey meaning, relying not only on the shape of symbols but also on their spatial arrangement in the page, and relative to each other. When presented in image form, these languages require specialized computational processing which is not the same as usually done either for natural language processing or for artificial vision. Quevedo enables this specialized processing, focusing on a data-based approach. As a command line application and library, it provides features for the collection and management of image datasets, and their machine learning recognition using neural networks and recognizer pipelines. This processing requires careful annotation of the source data, for which Quevedo offers an extensive and visual web-based annotation interface. In this article, we also briefly present a case study centered on the task of SignWriting recognition, the original motivation for writing the software. Quevedo is written in Python, and distributed freely under the Open Software License version 3.0.} } @inproceedings{mukushev-etal-2022-crowdsourcing:lrec, author = {Mukushev, Medet and Ubingazhibov, Aidyn and Kydyrbekova, Aigerim and Imashev, Alfarabi and Kimmelman, Vadim and Sandygulova, Anara}, title = {Crowdsourcing {Kazakh-Russian} {Sign} {Language}: {FluentSigners-50}}, pages = {2541--2547}, editor = {Calzolari, Nicoletta and B{\'e}chet, Fr{\'e}d{\'e}ric and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Odijk, Jan and Piperidis, Stelios}, booktitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {20--25}, month = jun, year = {2022}, isbn = {979-10-95546-72-6}, language = {english}, url = {https://aclanthology.org/2022.lrec-1.271}, doi = {10.63317/3azsxoosxde5}, abstract = {This paper presents the methodology we used to crowdsource a data collection of a new large-scale signer independent dataset for Kazakh-Russian Sign Language (KRSL) created for Sign Language Processing. By involving the Deaf community throughout the research process, we firstly designed a research protocol and then performed an efficient crowdsourcing campaign that resulted in a new FluentSigners-50 dataset. The FluentSigners-50 dataset consists of 173 sentences performed by 50 KRSL signers for 43,250 video samples. Dataset contributors recorded videos in real-life settings on various backgrounds using various devices such as smartphones and web cameras. Therefore, each dataset contribution has a varying distance to the camera, camera angles and aspect ratio, video quality, and frame rates. Additionally, the proposed dataset contains a high degree of linguistic and inter-signer variability and thus is a better training set for recognizing a real-life signed speech. FluentSigners-50 is publicly available at https://krslproject.github.io/fluentsigners-50/} } @inproceedings{van-den-heuvel-etal-2020-clarin:lrec, author = {van den Heuvel, Henk and Oostdijk, Nelleke and Rowland, Caroline and Trilsbeek, Paul}, title = {The {CLARIN} Knowledge Centre for Atypical Communication Expertise}, pages = {3312--3316}, editor = {Calzolari, Nicoletta and Fr{\'e}d{\'e}ric B{\'e}chet and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {11--16}, month = may, year = {2020}, isbn = {979-10-95546-34-4}, language = {english}, url = {https://aclanthology.org/2020.lrec-1.405}, doi = {10.63317/3kvav2y52ne6}, abstract = {This paper introduces a new CLARIN Knowledge Center which is the K-Centre for Atypical Communication Expertise (ACE for short) which has been established at the Centre for Language and Speech Technology (CLST) at Radboud University. Atypical communication is an umbrella term used here to denote language use by second language learners, people with language disorders or those suffering from language disabilities, but also more broadly by bilinguals and users of sign languages. It involves multiple modalities (text, speech, sign, gesture) and encompasses different developmental stages. ACE closely collaborates with The Language Archive (TLA) at the Max Planck Institute for Psycholinguistics in order to safeguard GDPR-compliant data storage and access. We explain the mission of ACE and show its potential on a number of showcases and a use case.} } @inproceedings{jantunen-etal-2020-comes:lrec, author = {Jantunen, Tommi and Puupponen, Anna and Burger, Birgitta}, title = {What Comes First: Combining Motion Capture and Eye Tracking Data to Study the Order of Articulators in Constructed Action in Sign Language Narratives}, pages = {6003--6007}, editor = {Calzolari, Nicoletta and Fr{\'e}d{\'e}ric B{\'e}chet and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {11--16}, month = may, year = {2020}, isbn = {979-10-95546-34-4}, language = {english}, url = {https://aclanthology.org/2020.lrec-1.735}, doi = {10.63317/2tkcwqupsu77}, abstract = {We use synchronized 120 fps motion capture and 50 fps eye tracking data from two native signers to investigate the temporal order in which the dominant hand, the head, the chest and the eyes start producing overt constructed action from regular narration in seven short Finnish Sign Language stories. From the material, we derive a sample of ten instances of regular narration to overt constructed action transfers in ELAN which we then further process and analyze in Matlab. The results indicate that the temporal order of articulators shows both contextual and individual variation but that there are also repeated patterns which are similar across all the analyzed sequences and signers. Most notably, when the discourse strategy changes from regular narration to overt constructed action, the head and the eyes tend to take the leading role, and the chest and the dominant hand tend to start acting last. Consequences of the findings are discussed.} } @inproceedings{naert-etal-2020-lsf:lrec, author = {Naert, Lucie and Larboulette, Caroline and Gibet, Sylvie}, title = {{LSF}-{ANIMAL}: A Motion Capture Corpus in {F}rench {S}ign {L}anguage Designed for the Animation of Signing Avatars}, pages = {6008--6017}, editor = {Calzolari, Nicoletta and Fr{\'e}d{\'e}ric B{\'e}chet and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {11--16}, month = may, year = {2020}, isbn = {979-10-95546-34-4}, language = {english}, url = {https://aclanthology.org/2020.lrec-1.736}, doi = {10.63317/2au25heifxfn}, abstract = {Signing avatars allow deaf people to access information in their preferred language using an interactive visualization of the sign language spatio-temporal content. However, avatars are often procedurally animated, resulting in robotic and unnatural movements, which are therefore rejected by the community for which they are intended. To overcome this lack of authenticity, solutions in which the avatar is animated from motion capture data are promising. Yet, the initial data set drastically limits the range of signs that the avatar can produce. Therefore, it can be interesting to enrich the initial corpus with new content by editing the captured motions. For this purpose, we collected the LSF-ANIMAL corpus, a French Sign Language (LSF) corpus composed of captured isolated signs and full sentences that can be used both to study LSF features and to generate new signs and utterances. This paper presents the precise definition and content of this corpus, technical considerations relative to the motion capture process (including the marker set definition), the post-processing steps required to obtain data in a standard motion format and the annotation scheme used to label the data. The quality of the corpus with respect to intelligibility, accuracy and realism is perceptually evaluated by 41 participants including native LSF signers.} } @inproceedings{de-coster-etal-2020-sign:lrec, author = {De Coster, Mathieu and Van Herreweghe, Mieke and Dambre, Joni}, title = {Sign Language Recognition with Transformer Networks}, pages = {6018--6024}, editor = {Calzolari, Nicoletta and Fr{\'e}d{\'e}ric B{\'e}chet and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {11--16}, month = may, year = {2020}, isbn = {979-10-95546-34-4}, language = {english}, url = {https://aclanthology.org/2020.lrec-1.737}, doi = {10.63317/3jf6p4jvn4ok}, abstract = {Sign languages are complex languages. Research into them is ongoing, supported by large video corpora of which only small parts are annotated. Sign language recognition can be used to speed up the annotation process of these corpora, in order to aid research into sign languages and sign language recognition. Previous research has approached sign language recognition in various ways, using feature extraction techniques or end-to-end deep learning. In this work, we apply a combination of feature extraction using OpenPose for human keypoint estimation and end-to-end feature learning with Convolutional Neural Networks. The proven multi-head attention mechanism used in transformers is applied to recognize isolated signs in the Flemish Sign Language corpus. Our proposed method significantly outperforms the previous state of the art of sign language recognition on the Flemish Sign Language corpus: we obtain an accuracy of 74.7{\%} on a vocabulary of 100 classes. Our results will be implemented as a suggestion system for sign language corpus annotation.} } @inproceedings{trolvi-delmonte-2020-annotating:lrec, author = {Trolvi, Serena and Delmonte, Rodolfo}, title = {Annotating a Fable in {I}talian {S}ign {L}anguage ({LIS})}, pages = {6025--6034}, editor = {Calzolari, Nicoletta and Fr{\'e}d{\'e}ric B{\'e}chet and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {11--16}, month = may, year = {2020}, isbn = {979-10-95546-34-4}, language = {english}, url = {https://aclanthology.org/2020.lrec-1.738}, doi = {10.63317/2twkssq4cznb}, abstract = {This paper introduces work carried out for the automatic generation of a written text in Italian starting from glosses of a fable in Italian Sign Language (LIS). The paper gives a brief overview of sign languages (SLs) and some peculiarities of SL fables such as the use of space, the strategy of Role Shift and classifiers. It also presents the annotation of the fable ''The Tortoise and the Hare'' - signed in LIS and made available by Alba Cooperativa Sociale -, which was annotated manually by first author for her master's thesis. The annotation was the starting point of a generation process that allowed us to automatically generate a text in Italian starting from LIS glosses. LIS sentences have been transcribed with Italian words into tables on simultaneous layers, each of which contains specific linguistic or non-linguistic pieces of information. In addition, the present work discusses problems encountered in the annotation and generation process.} } @inproceedings{neves-etal-2020-hamnosys2sigml:lrec, author = {Neves, Carolina and Coheur, Lu{\'i}sa and Nicolau, Hugo}, title = {{HamNoSys2SiGML}: Translating {HamNoSys} Into {SiGML}}, pages = {6035--6039}, editor = {Calzolari, Nicoletta and Fr{\'e}d{\'e}ric B{\'e}chet and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {11--16}, month = may, year = {2020}, isbn = {979-10-95546-34-4}, language = {english}, url = {https://aclanthology.org/2020.lrec-1.739}, doi = {10.63317/28pb5ow9to48}, abstract = {Sign Languages are visual languages and the main means of communication used by Deaf people. However, the majority of the information available online is presented through written form. Hence, it is not of easy access to the Deaf community. Avatars that can animate sign languages have gained an increase of interest in this area due to their flexibility in the process of generation and edition. Synthetic animation of conversational agents can be achieved through the use of notation systems. HamNoSys is one of these systems, which describes movements of the body through symbols. Its XML-compliant, SiGML, is a machine-readable input of HamNoSys able to animate avatars. Nevertheless, current tools have no freely available open source libraries that allow the conversion from HamNoSys to SiGML. Our goal is to develop a tool of open access, which can perform this conversion independently from other platforms. This system represents a crucial intermediate step in the bigger pipeline of animating signing avatars. Two cases studies are described in order to illustrate different applications of our tool.} } @inproceedings{belissen-etal-2020-dicta:lrec, author = {Belissen, Valentin and Braffort, Annelies and Gouiff{\`e}s, Mich{\`e}le}, title = {{D}icta-{S}ign-{LSF}-v2: Remake of a Continuous {F}rench {S}ign {L}anguage Dialogue Corpus and a First Baseline for Automatic Sign Language Processing}, pages = {6040--6048}, editor = {Calzolari, Nicoletta and Fr{\'e}d{\'e}ric B{\'e}chet and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {11--16}, month = may, year = {2020}, isbn = {979-10-95546-34-4}, language = {english}, url = {https://aclanthology.org/2020.lrec-1.740}, doi = {10.63317/3ws6bwnftg37}, abstract = {While the research in automatic Sign Language Processing (SLP) is growing, it has been almost exclusively focused on recognizing lexical signs, whether isolated or within continuous SL production. However, Sign Languages include many other gestural units like iconic structures, which need to be recognized in order to go towards a true SL understanding. In this paper, we propose a newer version of the publicly available SL corpus Dicta-Sign, limited to its French Sign Language part. Involving 16 different signers, this dialogue corpus was produced with very few constraints on the style and content. It includes lexical and non-lexical annotations over 11 hours of video recording, with 35000 manual units. With the aim of stimulating research in SL understanding, we also provide a baseline for the recognition of lexical signs and non-lexical structures on this corpus. A very compact modeling of a signer is built and a Convolutional-Recurrent Neural Network is trained and tested on Dicta-Sign-LSF-v2, with state-of-the-art results, including the ability to detect iconicity in SL production.} } @inproceedings{tornay-etal-2020-hmm:lrec, author = {Tornay, Sandrine and Aran, Oya and Magimai Doss, Mathew}, title = {An {HMM} Approach with Inherent Model Selection for Sign Language and Gesture Recognition}, pages = {6049--6056}, editor = {Calzolari, Nicoletta and Fr{\'e}d{\'e}ric B{\'e}chet and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {11--16}, month = may, year = {2020}, isbn = {979-10-95546-34-4}, language = {english}, url = {https://aclanthology.org/2020.lrec-1.741}, doi = {10.63317/4b3yi2mdmmgb}, abstract = {HMMs have been the one of the first models to be applied for sign recognition and have become the baseline models due to their success in modeling sequential and multivariate data. Despite the extensive use of HMMs for sign recognition, determining the HMM structure has still remained as a challenge, especially when the number of signs to be modeled is high. In this work, we present a continuous HMM framework for modeling and recognizing isolated signs, which inherently performs model selection to optimize the number of states for each sign separately during recognition. Our experiments on three different datasets, namely, German sign language DGS dataset, Turkish sign language HospiSign dataset and Chalearn14 dataset show that the proposed approach achieves better sign language or gesture recognition systems in comparison to the approach of selecting or presetting the number of HMM states based on k-means, and yields systems that perform competitive to the case where the number of states are determined based on the test set performance.} } @inproceedings{scicluna-strapparava-2020-vroav:lrec, author = {Scicluna, Simone and Strapparava, Carlo}, title = {{VROAV}: Using Iconicity to Visually Represent Abstract Verbs}, pages = {6057--6062}, editor = {Calzolari, Nicoletta and Fr{\'e}d{\'e}ric B{\'e}chet and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {11--16}, month = may, year = {2020}, isbn = {979-10-95546-34-4}, language = {english}, url = {https://aclanthology.org/2020.lrec-1.742}, doi = {10.63317/2mftaz38bmnf}, abstract = {For a long time, philosophers, linguists and scientists have been keen on finding an answer to the mind-bending question ``what does abstract language look like?'', which has also sprung from the phenomenon of mental imagery and how this emerges in the mind. One way of approaching the matter of word representations is by exploring the common semantic elements that link words to each other. Visual languages like sign languages have been found to reveal enlightening patterns across signs of similar meanings, pointing towards the possibility of identifying clusters of iconic meanings. With this insight, merged with an understanding of verb predicates achieved from VerbNet, this study presents a novel verb classification system based on visual shapes, using graphic animation to visually represent 20 classes of abstract verbs. Considerable agreement between participants who judged the graphic animations based on representativeness suggests a positive way forward for this proposal, which may be developed as a language learning aid in educational contexts or as a multimodal language comprehension tool for digital text.} } @inproceedings{bull-etal-2020-mediapi:lrec, author = {Bull, Hannah and Braffort, Annelies and Gouiff{\`e}s, Mich{\`e}le}, title = {{MEDIAPI}-{SKEL} - A 2{D}-Skeleton Video Database of {F}rench {S}ign {L}anguage With Aligned {F}rench Subtitles}, pages = {6063--6068}, editor = {Calzolari, Nicoletta and Fr{\'e}d{\'e}ric B{\'e}chet and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {11--16}, month = may, year = {2020}, isbn = {979-10-95546-34-4}, language = {english}, url = {https://aclanthology.org/2020.lrec-1.743}, doi = {10.63317/2dbizmkkckre}, abstract = {This paper presents MEDIAPI-SKEL, a 2D-skeleton database of French Sign Language videos aligned with French subtitles. The corpus contains 27 hours of video of body, face and hand keypoints, aligned to subtitles with a vocabulary size of 17k tokens. In contrast to existing sign language corpora such as videos produced under laboratory conditions or translations of TV programs into sign language, this database is constructed using original sign language content largely produced by deaf journalists at the media company M{\'e}dia-Pi. Moreover, the videos are accurately synchronized with French subtitles. We propose three challenges appropriate for this corpus that are related to processing units of signs in context: automatic alignment of text and video, semantic segmentation of sign language, and production of video-text embeddings for cross-modal retrieval. These challenges deviate from the classic task of identifying a limited number of lexical signs in a video stream.} } @inproceedings{kaczmarek-filhol-2020-alignment:lrec, author = {Kaczmarek, Marion and Filhol, Michael}, title = {Alignment Data base for a Sign Language Concordancer}, pages = {6069--6072}, editor = {Calzolari, Nicoletta and Fr{\'e}d{\'e}ric B{\'e}chet and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {11--16}, month = may, year = {2020}, isbn = {979-10-95546-34-4}, language = {english}, url = {https://aclanthology.org/2020.lrec-1.744}, doi = {10.63317/359s27nvfssb}, abstract = {This article deals with elaborating a data base of alignments of parallel Franch-LSF segments. This data base is meant to be searched using a concordancer which we are also designing. We wish to equip Sign Language translators with tools similar to those used in text-to-text translation. To do so, we need language resources to feed them. Already existing Sign Language corpora can be found, but do not match our needs: working around a Sign Language concordancer, the corpus must be a parallel one and provide various examples of vocabulary and grammatical construction. We started with a parallel corpus of 40 short news and 120 SL videos , which we aligned manually by segments of various length. We described the methodology we used, how we define our segments and alignments. The last part concerns how we hope to allow the data base to keep growing in a near future.} } @inproceedings{mukushev-etal-2020-evaluation:lrec, author = {Mukushev, Medet and Sabyrov, Arman and Imashev, Alfarabi and Koishybay, Kenessary and Kimmelman, Vadim and Sandygulova, Anara}, title = {Evaluation of Manual and Non-manual Components for Sign Language Recognition}, pages = {6073--6078}, editor = {Calzolari, Nicoletta and Fr{\'e}d{\'e}ric B{\'e}chet and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {11--16}, month = may, year = {2020}, isbn = {979-10-95546-34-4}, language = {english}, url = {https://aclanthology.org/2020.lrec-1.745}, doi = {10.63317/5bj5d22wctiy}, abstract = {The motivation behind this work lies in the need to differentiate between similar signs that differ in non-manual components present in any sign. To this end, we recorded full sentences signed by five native signers and extracted 5200 isolated sign samples of twenty frequently used signs in Kazakh-Russian Sign Language (K-RSL), which have similar manual components but differ in non-manual components (i.e. facial expressions, eyebrow height, mouth, and head orientation). We conducted a series of evaluations in order to investigate whether non-manual components would improve sign's recognition accuracy. Among standard machine learning approaches, Logistic Regression produced the best results, 78.2{\%} of accuracy for dataset with 20 signs and 77.9{\%} of accuracy for dataset with 2 classes (statement vs question). Dataset can be downloaded from the following website: https://krslproject.github.io/krsl20/} } @inproceedings{kagirov-etal-2020-theruslan:lrec, author = {Kagirov, Ildar and Ivanko, Denis and Ryumin, Dmitry and Axyonov, Alexander and Karpov, Alexey}, title = {{T}he{R}u{SL}an: Database of {R}ussian {S}ign {L}anguage}, pages = {6079--6085}, editor = {Calzolari, Nicoletta and Fr{\'e}d{\'e}ric B{\'e}chet and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {11--16}, month = may, year = {2020}, isbn = {979-10-95546-34-4}, language = {english}, url = {https://aclanthology.org/2020.lrec-1.746}, doi = {10.63317/56989mgt6hxy}, abstract = {In this paper, a new Russian sign language multimedia database TheRuSLan is presented. The database includes lexical units (single words and phrases) from Russian sign language within one subject area, namely, ``food products at the supermarket'', and was collected using MS Kinect 2.0 device including both FullHD video and the depth map modes, which provides new opportunities for the lexicographical description of the Russian sign language vocabulary and enhances research in the field of automatic gesture recognition. Russian sign language has an official status in Russia, and over 120,000 deaf people in Russia and its neighboring countries use it as their first language. Russian sign language has no writing system, is poorly described and belongs to the low-resource languages. The authors formulate the basic principles of annotation of sign words, based on the collected data, and reveal the content of the collected database. In the future, the database will be expanded and comprise more lexical units. The database is explicitly made for the task of creating an automatic system for Russian sign language recognition.} } @inproceedings{metaxas-etal-2018-linguistically:lrec, author = {Metaxas, Dimitris and Dilsizian, Mark and Neidle, Carol}, title = {Linguistically-driven Framework for Computationally Efficient and Scalable Sign Recognition}, pages = {1711--1718}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu}, booktitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {7--12}, month = may, year = {2018}, isbn = {979-10-95546-00-9}, language = {english}, url = {https://aclanthology.org/L18-1271}, doi = {10.63317/3p4cvkgxp7ru}, abstract = {We introduce a new general framework for sign recognition from monocular video using limited quantities of annotated data. The novelty of the hybrid framework we describe here is that we exploit state-of-the art learning methods while also incorporating features based on what we know about the linguistic composition of lexical signs. In particular, we analyze hand shape, orientation, location, and motion trajectories, and then use CRFs to combine this linguistically significant information for purposes of sign recognition. Our robust modeling and recognition of these sub-components of sign production allow an efficient parameterization of the sign recognition problem as compared with purely data-driven methods. This parameterization enables a scalable and extendable time-series learning approach that advances the state of the art in sign recognition, as shown by the results reported here for recognition of isolated, citation-form, lexical signs from American Sign Language (ASL).} } @inproceedings{cassidy-etal-2018-signbank:lrec, author = {Cassidy, Steve and Crasborn, Onno and Nieminen, Henri and Stoop, Wessel and Hulsbosch, Micha and Even, Susan and Komen, Erwin and Johnston, Trevor}, title = {{S}ignbank: Software to Support Web Based Dictionaries of Sign Language}, pages = {2359--2364}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu}, booktitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {7--12}, month = may, year = {2018}, isbn = {979-10-95546-00-9}, language = {english}, url = {https://aclanthology.org/L18-1374}, doi = {10.63317/39xy2jfsp733}, abstract = {Signbank is a web application that was originally built to support the Auslan Signbank on-line web dictionary, it was an Open Source re-implementation of an earlier version of that site. The application provides a framework for the development of a rich lexical database of sign language augmented with video samples of signs. As an Open Source project, the original Signbank has formed the basis of a number of new sign language dictionaries and corpora including those for British Sign Language, Sign Language of the Netherlands and Finnish Sign Language. Versions are under development for American Sign Language and Flemish Sign Language. This paper describes the overall architecture of the Signbank system and its representation of lexical entries and associated entities.} } @inproceedings{ebling-etal-2018-smile:lrec, author = {Ebling, Sarah and Camg{\"o}z, Necati Cihan and Boyes Braem, Penny and Tissi, Katja and Sidler-Miserez, Sandra and Stoll, Stephanie and Hadfield, Simon and Haug, Tobias and Bowden, Richard and Tornay, Sandrine and Razavi, Marzieh and Magimai Doss, Mathew}, title = {{SMILE} {S}wiss {G}erman Sign Language Dataset}, pages = {4221--4229}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu}, booktitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {7--12}, month = may, year = {2018}, isbn = {979-10-95546-00-9}, language = {english}, url = {https://aclanthology.org/L18-1666}, doi = {10.63317/3ygyk796mmfb}, abstract = {Sign language recognition (SLR) involves identifying the form and meaning of isolated signs or sequences of signs. To our knowledge, the combination of SLR and sign language assessment is novel. The goal of an ongoing three-year project in Switzerland is to pioneer an assessment system for lexical signs of Swiss German Sign Language (Deutschschweizerische Geb{\"a}rdensprache, DSGS) that relies on SLR. The assessment system aims to give adult L2 learners of DSGS feedback on the correctness of the manual parameters (handshape, hand position, location, and movement) of isolated signs they produce. In its initial version, the system will include automatic feedback for a subset of a DSGS vocabulary production test consisting of 100 lexical items. To provide the SLR component of the assessment system with sufficient training samples, a large-scale dataset containing videotaped repeated productions of the 100 items of the vocabulary test with associated transcriptions and annotations was created, consisting of data from 11 adult L1 signers and 19 adult L2 learners of DSGS. This paper introduces the dataset, which will be made available to the research community.} } @inproceedings{kimmelman-etal-2018-ipsl:lrec, author = {Kimmelman, Vadim and Klezovich, Anna and Moroz, George}, title = {{IPSL}: A Database of Iconicity Patterns in Sign Languages. Creation and Use}, pages = {4230--4234}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu}, booktitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {7--12}, month = may, year = {2018}, isbn = {979-10-95546-00-9}, language = {english}, url = {https://aclanthology.org/L18-1667}, doi = {10.63317/5jd6s9ekbgvt}, abstract = {We created the first large-scale database of signs annotated according to various parameters of iconicity. The signs represent concrete concepts in seven semantic fields in nineteen sign languages; 1542 signs in total. Each sign was annotated with respect to the type of form-image association, the presence of iconic location and movement, personification, and with respect to whether the sign depicts a salient part of the concept. We also created a website: https://sl-iconicity.shinyapps.io/iconicity patterns/ with several visualization tools to represent the data from the database. It is possible to visualize iconic properties of separate concepts or iconic properties of semantic fields on the map of the world, and to build graphs representing iconic patterns for selected semantic fields. A preliminary analysis of the data shows that iconicity patterns vary across semantic fields and across languages. The database and the website can be used to further study a variety of theoretical questions related to iconicity in sign languages.} } @inproceedings{yu-etal-2018-sign:lrec, author = {Yu, Shi and Geraci, Carlo and Abner, Natasha}, title = {Sign Languages and the Online World Online Dictionaries {\&} Lexicostatistics}, pages = {4235--4240}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu}, booktitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {7--12}, month = may, year = {2018}, isbn = {979-10-95546-00-9}, language = {english}, url = {https://aclanthology.org/L18-1668}, doi = {10.63317/3usp6u39to8i}, abstract = {Several online dictionaries documenting the lexicon of a variety of sign languages (SLs) are now available. These are rich resources for comparative studies, but there are methodological issues that must be addressed regarding how these resources are used for research purposes. We created a web-based tool for annotating the articulatory features of signs (handshape, location, movement and orientation). Videos from online dictionaries may be embedded in the tool, providing a mechanism for large-scale theoretically-informed sign language annotation. Annotations are saved in a spreadsheet format ready for quantitative and qualitative analyses. Here, we provide proof of concept for the utility of this tool in linguistic analysis. We used the SL adaptation of the Swadesh list (Woodward, 2000) and applied lexicostatistic and phylogenetic methods to a sample of 23 SLs coded using the web-based tool; supplementary historic information was gathered from the Ethnologue of World Languages and other online sources. We report results from the comparison of all articulatory features for four Asian SLs (Chinese, Hong Kong, Taiwanese and Japanese SLs) and from the comparison of handshapes on the entire 23 language sample. Handshape analysis of the entire sample clusters all Asian SLs together, separated from the European, American, and Brazilian SLs in the sample, as historically expected. Within the Asian SL cluster, analyses also show, for example, marginal relatedness between Chinese and Hong Kong SLs.} } @inproceedings{filhol-hadjadj-2018-elicitation:lrec, author = {Filhol, Michael and Hadjadj, Mohamed Nassime}, title = {Elicitation protocol and material for a corpus of long prepared monologues in Sign Language}, pages = {4241--4246}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu}, booktitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {7--12}, month = may, year = {2018}, isbn = {979-10-95546-00-9}, language = {english}, url = {https://aclanthology.org/L18-1669}, doi = {10.63317/2ktzfg3wberx}, abstract = {In this paper, we address collection of prepared Sign Language discourse, as opposed to spontaneous signing. Specifically, we aim at collecting long discourse, which creates problems explained in the paper. Being oral and visual languages, they cannot easily be produced while reading notes without distorting the data, and eliciting long discourse without influencing the production order is not trivial. For the moment, corpora contain either short productions, data distortion or disfluencies. We propose a protocol and two tasks with their elicitation material to allow cleaner long-discourse data, and evaluate the result of a recent test with LSF informants.} } @inproceedings{brock-nakadai-2018-deep:lrec, author = {Brock, Heike and Nakadai, Kazuhiro}, title = {Deep {JSLC}: A Multimodal Corpus Collection for Data-driven Generation of {J}apanese {S}ign {L}anguage Expressions}, pages = {4247--4252}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu}, booktitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {7--12}, month = may, year = {2018}, isbn = {979-10-95546-00-9}, language = {english}, url = {https://aclanthology.org/L18-1670}, doi = {10.63317/45x2kxh2c2e7}, abstract = {The three-dimensional visualization of spoken or written information in Sign Language (SL) is considered a potential tool for better inclusion of deaf or hard of hearing individuals with low literacy skills. However, conventional technologies for such CG-supported data display are not able to depict all relevant features of a natural signing sequence such as facial expression, spatial references or inter-sign movement, leading to poor acceptance amongst speakers of sign language. The deployment of fully data-driven, deep sequence generation models that proved themselves powerful in speech and text applications might overcome this lack of naturalness. Therefore, we collected a corpus of continuous sentence utterances in Japanese Sign Language (JSL) applicable to the learning of deep neural network models. The presented corpus contains multimodal content information of high resolution motion capture data, video data and both visual and gloss-like mark up annotations obtained with the support of fluent JSL signers. Furthermore, all annotations were encoded under three different encoding schemes with respect to directions, intonation and non-manual information. Currently, the corpus is employed to learn first sequence-to-sequence networks where it shows the ability to train relevant language features.} } @inproceedings{hadjadj-etal-2018-modeling:lrec, author = {Hadjadj, Mohamed Nassime and Filhol, Michael and Braffort, Annelies}, title = {Modeling {F}rench {S}ign {L}anguage: a proposal for a semantically compositional system}, pages = {4253--4258}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu}, booktitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {7--12}, month = may, year = {2018}, isbn = {979-10-95546-00-9}, language = {english}, url = {https://aclanthology.org/L18-1671}, doi = {10.63317/3mjavn7bk6fz}, abstract = {The recognition of French Sign Language (LSF) as a natural language in 2005 created an important need for the development of tools to make information accessible to the deaf public. With this prospect, the goal of this article is to propose a linguistic approach aimed at modeling the French sign language. We first present the models proposed in computer science to formalize the sign language (SL). We also show the difficulty of applying the grammars originally designed for spoken languages to model SL. In a second step, we propose an approach allowing to take into account the linguistic properties of the SL while respecting the constraints of a modelisation process. By studying the links between semantic functions and their observed forms in Corpus, we have identified several production rules that govern the functioning of the LSF. We finally present the rule functioning as a system capable of modeling an entire utterance in French Sign Language.} } @inproceedings{camgoz-etal-2016-bosphorussign:lrec, author = {Camg{\"o}z, Necati Cihan and K{\i}nd{\i}ro{\u g}lu, Ahmet Alp and Karab{\"u}kl{\"u}, Serpil and Kelepir, Meltem and {\"O}zsoy, Ay{\c s}e Sumru and Akarun, Lale}, title = {{B}osphorus{S}ign: A {T}urkish {S}ign {L}anguage Recognition Corpus in Health and Finance Domains}, pages = {1383--1388}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Goggi, Sara and Grobelnik, Marko and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {23--28}, month = may, year = {2016}, isbn = {978-2-9517408-9-1}, language = {english}, url = {https://aclanthology.org/L16-1220}, doi = {10.63317/2pb5x5mbf3yx}, abstract = {There are as many sign languages as there are deaf communities in the world. Linguists have been collecting corpora of different sign languages and annotating them extensively in order to study and understand their properties. On the other hand, the field of computer vision has approached the sign language recognition problem as a grand challenge and research efforts have intensified in the last 20 years. However, corpora collected for studying linguistic properties are often not suitable for sign language recognition as the statistical methods used in the field require large amounts of data. Recently, with the availability of inexpensive depth cameras, groups from the computer vision community have started collecting corpora with large number of repetitions for sign language recognition research. In this paper, we present the BosphorusSign Turkish Sign Language corpus, which consists of 855 sign and phrase samples from the health, finance and everyday life domains. The corpus is collected using the state-of-the-art Microsoft Kinect v2 depth sensor, and will be the first in this sign language research field. Furthermore, there will be annotations rendered by linguists so that the corpus will appeal both to the linguistic and sign language recognition research communities.} } @inproceedings{cabeza-pereiro-etal-2016-corilse:lrec, author = {Cabeza-Pereiro, Mar{\'i}a del Carmen and Garcia-Miguel, Jos{\'e} Ma and Mateo, Carmen Garc{\'i}a and Castro, Jos{\'e} Luis Alba}, title = {{CORILSE}: a {S}panish {S}ign {L}anguage Repository for Linguistic Analysis}, pages = {1402--1407}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Goggi, Sara and Grobelnik, Marko and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {23--28}, month = may, year = {2016}, isbn = {978-2-9517408-9-1}, language = {english}, url = {https://aclanthology.org/L16-1223}, doi = {10.63317/2phbuns7e3wj}, abstract = {CORILSE is a computerized corpus of Spanish Sign Language (Lengua de Signos Espa{\~n}ola, LSE). It consists of a set of recordings from different discourse genres by Galician signers living in the city of Vigo. In this paper we describe its annotation system, developed on the basis of pre-existing ones (mostly the model of Auslan corpus). This includes primary annotation of id-glosses for manual signs, annotation of non-manual component, and secondary annotation of grammatical categories and relations, because this corpus is been built for grammatical analysis, in particular argument structures in LSE. Up until this moment the annotation has been basically made by hand, which is a slow and time-consuming task. The need to facilitate this process leads us to engage in the development of automatic or semi-automatic tools for manual and facial recognition. Finally, we also present the web repository that will make the corpus available to different types of users, and will allow its exploitation for research purposes and other applications (e.g. teaching of LSE or design of tasks for signed language assessment).} } @inproceedings{becker-etal-2016-web:lrec, author = {Becker, Alex and Kepler, Fabio and Candeias, Sara}, title = {A Web Tool for Building Parallel Corpora of Spoken and Sign Languages}, pages = {1438--1445}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Goggi, Sara and Grobelnik, Marko and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {23--28}, month = may, year = {2016}, isbn = {978-2-9517408-9-1}, language = {english}, url = {https://aclanthology.org/L16-1229}, doi = {10.63317/5jz4u5ro86ej}, abstract = {In this paper we describe our work in building an online tool for manually annotating texts in any spoken language with SignWriting in any sign language. The existence of such tool will allow the creation of parallel corpora between spoken and sign languages that can be used to bootstrap the creation of efficient tools for the Deaf community. As an example, a parallel corpus between English and American Sign Language could be used for training Machine Learning models for automatic translation between the two languages. Clearly, this kind of tool must be designed in a way that it eases the task of human annotators, not only by being easy to use, but also by giving smart suggestions as the annotation progresses, in order to save time and effort. By building a collaborative, online, easy to use annotation tool for building parallel corpora between spoken and sign languages we aim at helping the development of proper resources for sign languages that can then be used in state-of-the-art models currently used in tools for spoken languages. There are several issues and difficulties in creating this kind of resource, and our presented tool already deals with some of them, like adequate text representation of a sign and many to many alignments between words and signs.} } @inproceedings{yanovich-etal-2016-detection:lrec, author = {Yanovich, Polina and Neidle, Carol and Metaxas, Dimitris}, title = {Detection of Major {ASL} Sign Types in Continuous Signing For {ASL} Recognition}, pages = {3067--3073}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Goggi, Sara and Grobelnik, Marko and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {23--28}, month = may, year = {2016}, isbn = {978-2-9517408-9-1}, language = {english}, url = {https://aclanthology.org/L16-1490}, doi = {10.63317/2ut664kbgkq3}, abstract = {In American Sign Language (ASL) as well as other signed languages, different classes of signs (e.g., lexical signs, fingerspelled signs, and classifier constructions) have different internal structural properties. Continuous sign recognition accuracy can be improved through use of distinct recognition strategies, as well as different training datasets, for each class of signs. For these strategies to be applied, continuous signing video needs to be segmented into parts corresponding to particular classes of signs. In this paper we present a multiple instance learning-based segmentation system that accurately labels 91.27{\%} of the video frames of 500 continuous utterances (including 7 different subjects) from the publicly accessible NCSLGR corpus (Neidle and Vogler, 2012). The system uses novel feature descriptors derived from both motion and shape statistics of the regions of high local motion. The system does not require a hand tracker.} } @inproceedings{bleicken-etal-2016-using:lrec, author = {Bleicken, Julian and Hanke, Thomas and Salden, Uta and Wagner, Sven}, title = {Using a Language Technology Infrastructure for {G}erman in order to Anonymize {G}erman {S}ign {L}anguage Corpus Data}, pages = {3303--3306}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Goggi, Sara and Grobelnik, Marko and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {23--28}, month = may, year = {2016}, isbn = {978-2-9517408-9-1}, language = {english}, url = {https://aclanthology.org/L16-1526}, doi = {10.63317/4ry2rahpi7et}, abstract = {For publishing sign language corpus data on the web, anonymization is crucial even if it is impossible to hide the visual appearance of the signers: In a small community, even vague references to third persons may be enough to identify those persons. In the case of the DGS Korpus (German Sign Language corpus) project, we want to publish data as a contribution to the cultural heritage of the sign language community while annotation of the data is still ongoing. This poses the question how well anonymization can be achieved given that no full linguistic analysis of the data is available. Basically, we combine analysis of all data that we have, including named entity recognition on translations into German. For this, we use the WebLicht language technology infrastructure. We report on the reliability of these methods in this special context and also illustrate how the anonymization of the video data is technically achieved in order to minimally disturb the viewer.} } @inproceedings{fotinea-etal-2016-multimodal:lrec, author = {Fotinea, Stavroula-Evita and Efthimiou, Eleni and Koutsombogera, Maria and Dimou, Athanasia-Lida and Goulas, Theodoros and Vasilaki, Kyriaki}, title = {Multimodal Resources for Human-Robot Communication Modelling}, pages = {3455--3460}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Goggi, Sara and Grobelnik, Marko and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {23--28}, month = may, year = {2016}, isbn = {978-2-9517408-9-1}, language = {english}, url = {https://aclanthology.org/L16-1551}, doi = {10.63317/3qza22q9uoo6}, abstract = {This paper reports on work related to the modelling of Human-Robot Communication on the basis of multimodal and multisensory human behaviour analysis. A primary focus in this framework of analysis is the definition of semantics of human actions in interaction, their capture and their representation in terms of behavioural patterns that, in turn, feed a multimodal human-robot communication system. Semantic analysis encompasses both oral and sign languages, as well as both verbal and non-verbal communicative signals to achieve an effective, natural interaction between elderly users with slight walking and cognitive inability and an assistive robotic platform.} } @inproceedings{meurant-etal-2016-modelling:lrec, author = {Meurant, Laurence and Gobert, Maxime and Cleve, Anthony}, title = {Modelling a Parallel Corpus of {F}rench and {F}rench {B}elgian {S}ign {L}anguage}, pages = {4236--4240}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Goggi, Sara and Grobelnik, Marko and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {23--28}, month = may, year = {2016}, isbn = {978-2-9517408-9-1}, language = {english}, url = {https://aclanthology.org/L16-1670}, doi = {10.63317/4wb9eoht5a48}, abstract = {The overarching objective underlying this research is to develop an online tool, based on a parallel corpus of French Belgian Sign Language (LSFB) and written Belgian French. This tool is aimed to assist various set of tasks related to the comparison of LSFB and French, to the benefit of general users as well as teachers in bilingual schools, translators and interpreters, as well as linguists. These tasks include (1) the comprehension of LSFB or French texts, (2) the production of LSFB or French texts, (3) the translation between LSFB and French in both directions and (4) the contrastive analysis of these languages. The first step of investigation aims at creating an unidirectional French-LSFB concordancer, able to align a one- or multiple-word expression from the French translated text with its corresponding expressions in the videotaped LSFB productions. We aim at testing the efficiency of this concordancer for the extraction of a dictionary of meanings in context. In this paper, we will present the modelling of the different data sources at our disposal and specifically the way they interact with one another.} } @inproceedings{wolfe-etal-2014-expanding:lrec, author = {Wolfe, Rosalee and McDonald, John C. and Berke, Larwan and Stumbo, Marie}, title = {Expanding n-gram analytics in {ELAN} and a case study for sign synthesis}, pages = {1880--1885}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Loftsson, Hrafn and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios,}, booktitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {26--31}, month = may, year = {2014}, isbn = {978-2-9517408-8-4}, language = {english}, url = {https://aclanthology.org/L14-1484}, doi = {10.63317/4mfef8xvv55v}, abstract = {Corpus analysis is a powerful tool for signed language synthesis. A new extension to ELAN offers expanded n-gram analysis tools including improved search capabilities and an extensive library of statistical measures of association for n-grams. Uncovering and exploring coarticulatory timing effects via corpus analysis requires n-gram analysis to discover the most frequently occurring bigrams. This paper presents an overview of the new tools and a case study in American Sign Language synthesis that exploits these capabilities for computing more natural timing in generated sentences. The new extension provides a time-saving convenience for language researchers using ELAN.} } @inproceedings{karppa-etal-2014-slmotion:lrec, author = {Karppa, Matti and Viitaniemi, Ville and Luzardo, Marcos and Laaksonen, Jorma and Jantunen, Tommi}, title = {{SLM}otion - An extensible sign language oriented video analysis tool}, pages = {1886--1891}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Loftsson, Hrafn and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios,}, booktitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {26--31}, month = may, year = {2014}, isbn = {978-2-9517408-8-4}, language = {english}, url = {https://aclanthology.org/L14-1208}, doi = {10.63317/4rncddrvjni8}, abstract = {We present a software toolkit called SLMotion which provides a framework for automatic and semiautomatic analysis, feature extraction and annotation of individual sign language videos, and which can easily be adapted to batch processing of entire sign language corpora. The program follows a modular design, and exposes a Numpy-compatible Python application programming interface that makes it easy and convenient to extend its functionality through scripting. The program includes support for exporting the annotations in ELAN format. The program is released as free software, and is available for GNU/Linux and MacOS platforms.} } @inproceedings{viitaniemi-etal-2014-pot:lrec, author = {Viitaniemi, Ville and Jantunen, Tommi and Savolainen, Leena and Karppa, Matti and Laaksonen, Jorma}, title = {{S}-pot - a benchmark in spotting signs within continuous signing}, pages = {1892--1897}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Loftsson, Hrafn and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios,}, booktitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {26--31}, month = may, year = {2014}, isbn = {978-2-9517408-8-4}, language = {english}, url = {https://aclanthology.org/L14-1377}, doi = {10.63317/5mv9tjhfyy5j}, abstract = {In this paper we present S-pot, a benchmark setting for evaluating the performance of automatic spotting of signs in continuous sign language videos. The benchmark includes 5539 video files of Finnish Sign Language, ground truth sign spotting results, a tool for assessing the spottings against the ground truth, and a repository for storing information on the results. In addition we will make our sign detection system and results made with it publicly available as a baseline for comparison and further developments.} } @inproceedings{bono-etal-2014-colloquial:lrec, author = {Bono, Mayumi and Kikuchi, Kouhei and Cibulka, Paul and Osugi, Yutaka}, title = {A Colloquial Corpus of {J}apanese {S}ign {L}anguage: Linguistic Resources for Observing Sign Language Conversations}, pages = {1898--1904}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Loftsson, Hrafn and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios,}, booktitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {26--31}, month = may, year = {2014}, isbn = {978-2-9517408-8-4}, language = {english}, url = {https://aclanthology.org/L14-1253}, doi = {10.63317/4vmxm7acgy5s}, abstract = {We began building a corpus of Japanese Sign Language (JSL) in April 2011. The purpose of this project was to increase awareness of sign language as a distinctive language in Japan. This corpus is beneficial not only to linguistic research but also to hearing-impaired and deaf individuals, as it helps them to recognize and respect their linguistic differences and communication styles. This is the first large-scale JSL corpus developed for both academic and public use. We collected data in three ways: interviews (for introductory purposes only), dialogues, and lexical elicitation. In this paper, we focus particularly on data collected during a dialogue to discuss the application of conversation analysis (CA) to signed dialogues and signed conversations. Our annotation scheme was designed not only to elucidate theoretical issues related to grammar and linguistics but also to clarify pragmatic and interactional phenomena related to the use of JSL.} } @inproceedings{geer-keane-2014-exploring:lrec, author = {Geer, Leah and Keane, Jonathan}, title = {Exploring factors that contribute to successful fingerspelling comprehension}, pages = {1905--1910}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Loftsson, Hrafn and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios,}, booktitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {26--31}, month = may, year = {2014}, isbn = {978-2-9517408-8-4}, language = {english}, url = {https://aclanthology.org/L14-1319}, doi = {10.63317/34bngdwsjqh2}, abstract = {Using a novel approach, we examine which cues in a fingerspelling stream, namely holds or transitions, allow for more successful comprehension by students learning American Sign Language (ASL). Sixteen university-level ASL students participated in this study. They were shown video clips of a native signer fingerspelling common English words. Clips were modified in the following ways: all were slowed down to half speed, one-third of the clips were modified to black out the transition portion of the fingerspelling stream, and one-third modified to have holds blacked out. The remaining third of clips were free of blacked out portions, which we used to establish a baseline of comprehension. Research by Wilcox (1992), among others, suggested that transitions provide more rich information, and thus items with the holds blacked out should be easier to comprehend than items with the transitions blacked out. This was not found to be the case here. Students achieved higher comprehension scores when hold information was provided. Data from this project can be used to design training tools to help students become more proficient at fingerspelling comprehension, a skill with which most students struggle.} } @inproceedings{forster-etal-2014-extensions:lrec, author = {Forster, Jens and Schmidt, Christoph and Koller, Oscar and Bellgardt, Martin and Ney, Hermann}, title = {Extensions of the Sign Language Recognition and Translation Corpus {RWTH}-{PHOENIX}-{Weather}}, pages = {1911--1916}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Loftsson, Hrafn and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios,}, booktitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {26--31}, month = may, year = {2014}, isbn = {978-2-9517408-8-4}, language = {english}, url = {https://aclanthology.org/L14-1472}, doi = {10.63317/27pdd6xpkah6}, abstract = {This paper introduces the RWTH-PHOENIX-Weather 2014, a video-based, large vocabulary, German sign language corpus which has been extended over the last two years, tripling the size of the original corpus. The corpus contains weather forecasts simultaneously interpreted into sign language which were recorded from German public TV and manually annotated using glosses on the sentence level and semi-automatically transcribed spoken German extracted from the videos using the open-source speech recognition system RASR. Spatial annotations of the signers' hands as well as shape and orientation annotations of the dominant hand have been added for more than 40k respectively 10k video frames creating one of the largest corpora allowing for quantitative evaluation of object tracking algorithms. Further, over 2k signs have been annotated using the SignWriting annotation system, focusing on the shape, orientation, movement as well as spatial contacts of both hands. Finally, extended recognition and translation setups are defined, and baseline results are presented.} } @inproceedings{hochgesang-2014-use:lrec, author = {Hochgesang, Julie A.}, title = {The Use of a {FileMaker} {Pro} Database in Evaluating Sign Language Notation Systems}, pages = {1917--1923}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Loftsson, Hrafn and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios,}, booktitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {26--31}, month = may, year = {2014}, isbn = {978-2-9517408-8-4}, language = {english}, url = {https://aclanthology.org/L14-1506}, doi = {10.63317/3px4stkwyyk8}, abstract = {In this paper, FileMaker Pro has been used to create a database in order to evaluate sign language notation systems used for representing hand configurations. The database cited in this paper focuses on child acquisition data, particularly the dataset of one child and one adult productions of the same American Sign Language (ASL) signs produced in a two-year span. The hand configurations in selected signs have been coded using Stokoe notation (Stokoe, Casterline {\&} Croneberg, 1965), the Hamburg Notation System or HamNoSys (Prillwitz et al, 1989), the revised Prosodic Model Handshape Coding system or PM (Eccarius {\&} Brentari, 2008) and Sign Language Phonetic Annotation or SLPA, a notation system that has grown from the Movement-Hold Model (Johnson {\&} Liddell, 2010, 2011a, 2011b, 2012). Data was pulled from ELAN transcripts, organized and notated in a FileMaker Pro database created to investigate the representativeness of each system. Representativeness refers to the ability of the notation system to represent the hand configurations in the dataset. This paper briefly describes the design of the FileMaker Pro database intended to provide both quantitative and qualitative information in order to allow the sign language researcher to examine the representativeness of sign language notation systems.} } @inproceedings{dilsizian-etal-2014-new:lrec, author = {Dilsizian, Mark and Yanovich, Polina and Wang, Shu and Neidle, Carol and Metaxas, Dimitris}, title = {A New Framework for Sign Language Recognition based on 3{D} Handshape Identification and Linguistic Modeling}, pages = {1924--1929}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Loftsson, Hrafn and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios,}, booktitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {26--31}, month = may, year = {2014}, isbn = {978-2-9517408-8-4}, language = {english}, url = {https://aclanthology.org/L14-1096}, doi = {10.63317/5evcpoxgej5n}, abstract = {Current approaches to sign recognition by computer generally have at least some of the following limitations: they rely on laboratory conditions for sign production, are limited to a small vocabulary, rely on 2D modeling (and therefore cannot deal with occlusions and off-plane rotations), and/or achieve limited success. Here we propose a new framework that (1) provides a new tracking method less dependent than others on laboratory conditions and able to deal with variations in background and skin regions (such as the face, forearms, or other hands); (2) allows for identification of 3D hand configurations that are linguistically important in American Sign Language (ASL); and (3) incorporates statistical information reflecting linguistic constraints in sign production. For purposes of large-scale computer-based sign language recognition from video, the ability to distinguish hand configurations accurately is critical. Our current method estimates the 3D hand configuration to distinguish among 77 hand configurations linguistically relevant for ASL. Constraining the problem in this way makes recognition of 3D hand configuration more tractable and provides the information specifically needed for sign recognition. Further improvements are obtained by incorporation of statistical information about linguistic dependencies among handshapes within a sign derived from an annotated corpus of almost 10,000 sign tokens.} } @inproceedings{liu-etal-2014-3d:lrec, author = {Liu, Bo and Liu, Jingjing and Yu, Xiang and Metaxas, Dimitris and Neidle, Carol}, title = {3{D} Face Tracking and Multi-Scale, Spatio-temporal Analysis of Linguistically Significant Facial Expressions and Head Positions in {ASL}}, pages = {4512--4518}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Loftsson, Hrafn and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios,}, booktitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Reykjavik, Iceland}, day = {26--31}, month = may, year = {2014}, isbn = {978-2-9517408-8-4}, language = {english}, url = {https://aclanthology.org/L14-1318}, doi = {10.63317/3oskdw9s6th8}, abstract = {Essential grammatical information is conveyed in signed languages by clusters of events involving facial expressions and movements of the head and upper body. This poses a significant challenge for computer-based sign language recognition. Here, we present new methods for the recognition of nonmanual grammatical markers in American Sign Language (ASL) based on: (1) new 3D tracking methods for the estimation of 3D head pose and facial expressions to determine the relevant low-level features; (2) methods for higher-level analysis of component events (raised/lowered eyebrows, periodic head nods and head shakes) used in grammatical markings―with differentiation of temporal phases (onset, core, offset, where appropriate), analysis of their characteristic properties, and extraction of corresponding features; (3) a 2-level learning framework to combine low- and high-level features of differing spatio-temporal scales. This new approach achieves significantly better tracking and recognition results than our previous methods.} } @inproceedings{gebre-etal-2012-towards:lrec, author = {Gebre, Binyam Gebrekidan and Wittenburg, Peter and Lenkiewicz, Przemyslaw}, title = {Towards Automatic Gesture Stroke Detection}, pages = {231--235}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u g}an, Mehmet U{\u g}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {21--27}, month = may, year = {2012}, isbn = {978-2-9517408-7-7}, language = {english}, url = {https://aclanthology.org/L12-1240}, doi = {10.63317/4svi55oz33nk}, abstract = {Automatic annotation of gesture strokes is important for many gesture and sign language researchers. The unpredictable diversity of human gestures and video recording conditions require that we adopt a more adaptive case-by-case annotation model. In this paper, we present a work-in progress annotation model that allows a user to a) track hands/face b) extract features c) distinguish strokes from non-strokes. The hands/face tracking is done with color matching algorithms and is initialized by the user. The initialization process is supported with immediate visual feedback. Sliders are also provided to support a user-friendly adjustment of skin color ranges. After successful initialization, features related to positions, orientations and speeds of tracked hands/face are extracted using unique identifiable features (corners) from a window of frames and are used for training a learning algorithm. Our preliminary results for stroke detection under non-ideal video conditions are promising and show the potential applicability of our methodology.} } @inproceedings{metaxas-etal-2012-recognition:lrec, author = {Metaxas, Dimitris and Liu, Bo and Yang, Fei and Yang, Peng and Michael, Nicholas and Neidle, Carol}, title = {Recognition of Nonmanual Markers in {A}merican {S}ign {L}anguage ({ASL}) Using Non-Parametric Adaptive 2{D}-3{D} Face Tracking}, pages = {2414--2420}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u g}an, Mehmet U{\u g}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {21--27}, month = may, year = {2012}, isbn = {978-2-9517408-7-7}, language = {english}, url = {https://aclanthology.org/L12-1123}, doi = {10.63317/2uye4hdfzb8j}, abstract = {This paper addresses the problem of automatically recognizing linguistically significant nonmanual expressions in American Sign Language from video. We develop a fully automatic system that is able to track facial expressions and head movements, and detect and recognize facial events continuously from video. The main contributions of the proposed framework are the following: (1) We have built a stochastic and adaptive ensemble of face trackers to address factors resulting in lost face track; (2) We combine 2D and 3D deformable face models to warp input frames, thus correcting for any variation in facial appearance resulting from changes in 3D head pose; (3) We use a combination of geometric features and texture features extracted from a canonical frontal representation. The proposed new framework makes it possible to detect grammatically significant nonmanual expressions from continuous signing and to differentiate successfully among linguistically significant expressions that involve subtle differences in appearance. We present results that are based on the use of a dataset containing 330 sentences from videos that were collected and linguistically annotated at Boston University.} } @inproceedings{karppa-etal-2012-comparing:lrec, author = {Karppa, Matti and Jantunen, Tommi and Viitaniemi, Ville and Laaksonen, Jorma and Burger, Birgitta and De Weerdt, Danny}, title = {Comparing computer vision analysis of signed language video with motion capture recordings}, pages = {2421--2425}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u g}an, Mehmet U{\u g}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {21--27}, month = may, year = {2012}, isbn = {978-2-9517408-7-7}, language = {english}, url = {https://aclanthology.org/L12-1152}, doi = {10.63317/52p5hwnr97hd}, abstract = {We consider a non-intrusive computer-vision method for measuring the motion of a person performing natural signing in video recordings. The quality and usefulness of the method is compared to a traditional marker-based motion capture set-up. The accuracy of descriptors extracted from video footage is assessed qualitatively in the context of sign language analysis by examining if the shape of the curves produced by the different means resemble one another in sequences where the shape could be a source of valuable linguistic information. Then, quantitative comparison is performed first by correlating the computer-vision-based descriptors with the variables gathered with the motion capture equipment. Finally, multivariate linear and non-linar regression methods are applied for predicting the motion capture variables based on combinations of computer vision descriptors. The results show that even the simple computer vision method evaluated in this paper can produce promisingly good results for assisting researchers working on sign language analysis.} } @inproceedings{braffort-boutora-2012-degels1:lrec, author = {Braffort, Annelies and Boutora, Le{\"i}la}, title = {{DEGELS}1: A comparable corpus of {F}rench {S}ign {L}anguage and co-speech gestures}, pages = {2426--2429}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u g}an, Mehmet U{\u g}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {21--27}, month = may, year = {2012}, isbn = {978-2-9517408-7-7}, language = {english}, url = {https://aclanthology.org/L12-1432}, doi = {10.63317/5dgbo563rhvs}, abstract = {In this paper, we describe DEGELS1, a comparable corpus of French Sign Language and co-speech gestures that has been created to serve as a testbed corpus for the DEGELS workshops. These workshop series were initiated in France for researchers studying French Sign Language and co-speech gestures in French, with the aim of comparing methodologies for corpus annotation. An extract was used for the first event DEGELS2011 dedicated to the annotation of pointing, and the same extract will be used for DEGELS2012, dedicated to segmentation.} } @inproceedings{gonzalez-etal-2012-semi:lrec, author = {Gonzalez, Matilde and Filhol, Michael and Collet, Christophe}, title = {Semi-Automatic Sign Language Corpora Annotation using Lexical Representations of Signs}, pages = {2430--2434}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u g}an, Mehmet U{\u g}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {21--27}, month = may, year = {2012}, isbn = {978-2-9517408-7-7}, language = {english}, url = {https://aclanthology.org/L12-1433}, doi = {10.63317/2pw3ppurxmdo}, abstract = {Nowadays many researches focus on the automatic recognition of sign language. High recognition rates are achieved using lot of training data. This data is, generally, collected by manual annotating SL video corpus. However this is time consuming and the results depend on the annotators knowledge. In this work we intend to assist the annotation in terms of glosses which consist on writing down the sign meaning sign for sign thanks to automatic video processing techniques. In this case using learning data is not suitable since at the first step it will be needed to manually annotate the corpus. Also the context dependency of signs and the co-articulation effect in continuous SL make the collection of learning data very difficult. Here we present a novel approach which uses lexical representations of sign to overcome these problems and image processing techniques to match sign performances to sign representations. Signs are described using Zeebede (ZBD) which is a descriptor of signs that considers the high variability of signs. A ZBD database is used to stock signs and can be queried using several characteristics. From a video corpus sequence features are extracted using a robust body part tracking approach and a semi-automatic sign segmentation algorithm. Evaluation has shown the performances and limitation of the proposed approach.} } @inproceedings{shoaib-etal-2012-platform:lrec, author = {Shoaib, Umar and Ahmad, Nadeem and Prinetto, Paolo and Tiotto, Gabriele}, title = {A platform-independent user-friendly dictionary from {I}talian to {LIS}}, pages = {2435--2438}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u g}an, Mehmet U{\u g}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {21--27}, month = may, year = {2012}, isbn = {978-2-9517408-7-7}, language = {english}, url = {https://aclanthology.org/L12-1541}, doi = {10.63317/4qz76f8v4uq5}, abstract = {The Lack of written representation for Italian Sign Language (LIS) makes it difficult to do perform tasks like looking up a new word in a dictionary. Most of the paper dictionaries show LIS signs in drawings or pictures. It's not a simple proposition to understand the meaning of sign from paper dictionaries unless one already knows the meanings. This paper presents the LIS dictionary which provides the facility to translate Italian text into sign language. LIS signs are shown as video animations performed by a virtual character. The LIS dictionary provides the integration with MultiWordNet database. The integration with MultiWordNet allows a rich extension with the meanings and senses of the words existing in MultiWordNet. The dictionary allows users to acquire information about lemmas, synonyms and synsets in the Sign Language (SL). The application is platform independent and can be used on any operating system. The results of input lemmas are displayed in groups of grammatical categories.} } @inproceedings{gavrilov-etal-2012-detecting:lrec, author = {Gavrilov, Zoya and Sclaroff, Stan and Neidle, Carol and Dickinson, Sven}, title = {Detecting Reduplication in Videos of {A}merican {S}ign {L}anguage}, pages = {3767--3773}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u g}an, Mehmet U{\u g}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {21--27}, month = may, year = {2012}, isbn = {978-2-9517408-7-7}, language = {english}, url = {https://aclanthology.org/L12-1057}, doi = {10.63317/3iqewee2q6mv}, abstract = {A framework is proposed for the detection of reduplication in digital videos of American Sign Language (ASL). In ASL, reduplication is used for a variety of linguistic purposes, including overt marking of plurality on nouns, aspectual inflection on verbs, and nominalization of verbal forms. Reduplication involves the repetition, often partial, of the articulation of a sign. In this paper, the apriori algorithm for mining frequent patterns in data streams is adapted for finding reduplication in videos of ASL. The proposed algorithm can account for varying weights on items in the apriori algorithm's input sequence. In addition, the apriori algorithm is extended to allow for inexact matching of similar hand motion subsequences and to provide robustness to noise. The formulation is evaluated on 105 lexical signs produced by two native signers. To demonstrate the formulation, overall hand motion direction and magnitude are considered; however, the formulation should be amenable to combining these features with others, such as hand shape, orientation, and place of articulation.} } @inproceedings{ivanova-eriksen-2012-bibikit:lrec, author = {Ivanova, Nedelina and Eriksen, Olle}, title = {{BiBiKit} - A Bilingual Bimodal Reading and Writing Tool for Sign Language Users}, pages = {3774--3778}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u g}an, Mehmet U{\u g}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {21--27}, month = may, year = {2012}, isbn = {978-2-9517408-7-7}, language = {english}, url = {https://aclanthology.org/L12-1061}, doi = {10.63317/35qcdxns4aie}, abstract = {Sign language is used by many people who were born deaf or who became deaf early in life use as their first and/or preferred language. There is no writing system for sign languages; texts are signed on video. As a consequence, texts in sign language are hard to navigate, search and annotate. The BiBiKit project is an easy to use authoring kit which is being developed and enables students, teachers, and virtually everyone to write and read bilingual bimodal texts and thereby creating electronic productions, which link text to sign language video. The main purpose of the project is to develop software that enables the user to link text to video, at the word, phrase and/or sentence level. The software will be developed for sign language and vice versa, but can be used to easily link text to any video: e.g. to add annotations, captions, or navigation points. The three guiding principles are: Software that is 1) stable, 2) easy to use, and 3) foolproof. A web based platform will be developed so the software is available whenever and wherever.} } @inproceedings{borgia-etal-2012-resource:lrec, author = {Borgia, Fabrizio and Bianchini, Claudia S. and Dalle, Patrice and De Marsico, Maria}, title = {Resource production of written forms of Sign Languages by a user-centered editor, {SW}ift ({S}ign{W}riting improved fast transcriber)}, pages = {3779--3784}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u g}an, Mehmet U{\u g}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {21--27}, month = may, year = {2012}, isbn = {978-2-9517408-7-7}, language = {english}, url = {https://aclanthology.org/L12-1210}, doi = {10.63317/5mxcr5ow296a}, abstract = {The SignWriting improved fast transcriber (SWift), presented in this paper, is an advanced editor for computer-aided writing and transcribing of any Sign Language (SL) using the SignWriting (SW). The application is an editor which allows composing and saving desired signs using the SW elementary components, called ``glyphs''. These make up a sort of alphabet, which does not depend on the national Sign Language and which codes the basic components of any sign. The user is guided through a fully automated procedure making the composition process fast and intuitive. SWift pursues the goal of helping to break down the ``electronic'' barriers that keep deaf people away from the web, and at the same time to support linguistic research about Sign Languages features. For this reason it has been designed with a special attention to deaf user needs, and to general usability issues. The editor has been developed in a modular way, so it can be integrated everywhere the use of the SW as an alternative to written ``verbal'' language may be advisable.} } @inproceedings{forster-etal-2012-rwth:lrec, author = {Forster, Jens and Schmidt, Christoph and Hoyoux, Thomas and Koller, Oscar and Zelle, Uwe and Piater, Justus and Ney, Hermann}, title = {{RWTH}-{PHOENIX}-{Weather}: A Large Vocabulary Sign Language Recognition and Translation Corpus}, pages = {3785--3789}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u g}an, Mehmet U{\u g}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {21--27}, month = may, year = {2012}, isbn = {978-2-9517408-7-7}, language = {english}, url = {https://aclanthology.org/L12-1503}, doi = {10.63317/4vmmiu4jeew5}, abstract = {This paper introduces the RWTH-PHOENIX-Weather corpus, a video-based, large vocabulary corpus of German Sign Language suitable for statistical sign language recognition and translation. In contrastto most available sign language data collections, the RWTH-PHOENIX-Weather corpus has not been recorded for linguistic research but for the use in statistical pattern recognition. The corpus contains weather forecasts recorded from German public TV which are manually annotated using glosses distinguishing sign variants, and time boundaries have been marked on the sentence and the gloss level. Further, the spoken German weather forecast has been transcribed in a semi-automatic fashion using a state-of-the-art automatic speech recognition system. Moreover, an additional translation of the glosses into spoken German has been created to capture allowable translation variability. In addition to the corpus, experimental baseline results for hand and head tracking, statistical sign language recognition and translation are presented.} } @inproceedings{crasborn-2010-sign:lrec, author = {Crasborn, Onno}, title = {The {Sign} {Linguistics} {Corpora} {Network}: Towards Standards for Signed Language Resources}, pages = {457--460}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Rosner, Mike and Tapias, Daniel}, booktitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {17--23}, month = may, year = {2010}, isbn = {978-2-9517408-6-0}, language = {english}, url = {https://aclanthology.org/L10-1009}, doi = {10.63317/2f4rj2gwqbsn}, abstract = {The Sign Linguistics Corpora Network is a three-year network initiative that aims to collect existing knowledge and practices on the creation and use of signed language resources. The concrete goals are to organise a series of four workshops in 2009 and 2010, create a stable Internet location for such knowledge, and generate new ideas for employing the most recent technologies for the study of signed languages. The network covers a wide range of subjects: data collection, metadata, annotation, and exploitation; these are the topics of the four workshops. The outcomes of the first two workshops are summarised in this paper; both workshops demonstrated that the need for dedicated knowledge on sign language corpora is especially salient in countries where researchers work alone or in small groups, which is still quite common in many places in Europe. While the original goal of the network was primarily to focus on corpus linguistics and language documentation, human language technology has gradually been incorporated as a user group of signed language resources.} } @inproceedings{duarte-gibet-2010-heterogeneous:lrec, author = {Duarte, Kyle and Gibet, Sylvie}, title = {Heterogeneous Data Sources for Signed Language Analysis and Synthesis: The {SignCom} Project}, pages = {461--468}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Rosner, Mike and Tapias, Daniel}, booktitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {17--23}, month = may, year = {2010}, isbn = {978-2-9517408-6-0}, language = {english}, url = {https://aclanthology.org/L10-1289}, doi = {10.63317/3m384eu67i8a}, abstract = {This paper describes how heterogeneous data sources captured in the SignCom project may be used for the analysis and synthesis of French Sign Language (LSF) utterances. The captured data combine video data and multimodal motion capture (mocap) data, including body and hand movements as well as facial expressions. These data are pre-processed, synchronized, and enriched by text annotations of signed language elicitation sessions. The addition of mocap data to traditional data structures provides additional phonetic data to linguists who desire to better understand the various parts of signs (handshape, movement, orientation, etc.) to very exacting levels, as well as their interactions and relative timings. We show how the phonologies of hand configurations and articulator movements may be studied using signal processing and statistical analysis tools to highlight regularities or temporal schemata between the different modalities. Finally, mocap data allows us to replay signs using a computer animation engine, specifically editing and rearranging movements and configurations in order to create novel utterances.} } @inproceedings{balvet-etal-2010-creagest:lrec, author = {Balvet, Antonio and Courtin, Cyril and Boutet, Dominique and Cuxac, Christian and Fusellier-Souza, Ivani and Garcia, Brigitte and L'Huillier, Marie-Th{\'e}r{\`e}se and Sallandre, Marie-Anne}, title = {The Creagest Project: a Digitized and Annotated Corpus for {F}rench {S}ign {L}anguage ({LSF}) and Natural Gestural Languages}, pages = {469--475}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Rosner, Mike and Tapias, Daniel}, booktitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {17--23}, month = may, year = {2010}, isbn = {978-2-9517408-6-0}, language = {english}, url = {https://aclanthology.org/L10-1245}, doi = {10.63317/3ufjdtshhebw}, abstract = {In this paper, we discuss the theoretical, sociolinguistic, methodological and technical objectives and issues of the French Creagest Project (2007-2012) in setting up, documenting and annotating a large corpus of adult and child French Sign Language (LSF) and of natural gestural language. The main objective of this ANR-funded research project is to set up a collaborative web-based platform for the study of semiogenesis in LSF (French Sign Language), i.e. the study of emerging structures and signs, be they used by Deaf adult signers, Deaf children, or even by Deaf and hearing subjects in interaction. In section 2, we address theoretical and practical issues, emphasizing the outstanding features of the Creagest Project. In section 3, we deal with methodological issues for data collection. Finally, in section 4, we examine technical aspects of LSF video data editing and corpus annotation, in the perspective of setting up a corpus-based formalized description of LSF.} } @inproceedings{dreuw-etal-2010-signspeak:lrec, author = {Dreuw, Philippe and Ney, Hermann and Mart{\'i}nez Ruiz, Gregorio and Crasborn, Onno and Piater, Justus and Moya Lazaro, Jos{\'e} Miguel and Wheatley, Mark}, title = {The {SignSpeak} Project - Bridging the Gap Between Signers and Speakers}, pages = {476--481}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Rosner, Mike and Tapias, Daniel}, booktitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {17--23}, month = may, year = {2010}, isbn = {978-2-9517408-6-0}, language = {english}, url = {https://aclanthology.org/L10-1238}, doi = {10.63317/4omuh5dhw6za}, abstract = {The SignSpeak project will be the first step to approach sign language recognition and translation at a scientific level already reached in similar research fields such as automatic speech recognition or statistical machine translation of spoken languages. Deaf communities revolve around sign languages as they are their natural means of communication. Although deaf, hard of hearing and hearing signers can communicate without problems amongst themselves, there is a serious challenge for the deaf community in trying to integrate into educational, social and work environments. The overall goal of SignSpeak is to develop a new vision-based technology for recognizing and translating continuous sign language to text. New knowledge about the nature of sign language structure from the perspective of machine recognition of continuous sign language will allow a subsequent breakthrough in the development of a new vision-based technology for continuous sign language recognition and translation. Existing and new publicly available corpora will be used to evaluate the research progress throughout the whole project.} } @inproceedings{lefebvre-albaret-dalle-2010-video:lrec, author = {Lefebvre-Albaret, Fran{\c c}ois and Dalle, Patrice}, title = {Video Retrieval in Sign Language Videos : How to Model and Compare Signs?}, pages = {3049--3054}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Rosner, Mike and Tapias, Daniel}, booktitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {17--23}, month = may, year = {2010}, isbn = {978-2-9517408-6-0}, language = {english}, url = {https://aclanthology.org/L10-1116}, doi = {10.63317/3satm5zceu3s}, abstract = {This paper deals with the problem of finding sign occurrences in a sign language (SL) video. It begins with an analysis of sign models and the way they can take into account the sign variability. Then, we review the most popular technics dedicated to automatic sign language processing and we focus on their adaptation to model sign variability. We present a new method to provide a parametric description of the sign as a set of continuous and discrete parameters. Signs are classified according to there categories (ballistic movements, circles ...), the symmetry between the hand movements, hand absolute and relative locations. Membership grades to sign categories and continuous parameter comparisons can be combined to estimate the similarity between two signs. We set out our system and we evaluate how much time can be saved when looking for a sign in a french sign language video. By now, our formalism only uses hand 2D locations, we finally discuss about the way of integrating other parameters as hand shape or facial expression in our framework.} } @inproceedings{hawayek-etal-2010-bilingual:lrec, author = {Hawayek, Antoinette and Del Gratta, Riccardo and Cappelli, Giuseppe}, title = {A Bilingual Dictionary {M}exican {S}ign {L}anguage-{S}panish/{S}panish-{M}exican {S}ign {L}anguage}, pages = {3055--3060}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Rosner, Mike and Tapias, Daniel}, booktitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {17--23}, month = may, year = {2010}, isbn = {978-2-9517408-6-0}, language = {english}, url = {https://aclanthology.org/L10-1010}, doi = {10.63317/5ju75y76c3uk}, abstract = {We present a three-part bilingual specialized dictionary Mexican Sign Language-Spanish / Spanish-Mexican Sign Language. This dictionary will be the outcome of a three-years agreement between the Italian “Consiglio Nazionale delle Ricerche” and the Mexican Conacyt. Although many other sign language dictionaries have been provided to deaf communities, there are no Mexican Sign Language dictionaries in Mexico, yet. We want to stress on the specialized feature of the proposed dictionary: the bilingual dictionary will contain frequently used general Spanish forms along with scholastic course specific specialized words whose meanings warrant comprehension of school curricula. We emphasize that this aspect of the bilingual dictionary can have a deep social impact, since we will furnish to deaf people the possibility to get competence in official language, which is necessary to ensure access to school curriculum and to become full-fledged citizens. From a technical point of view, the dictionary consists of a relational database, where we have saved the sign parameters and a graphical user interface especially designed to allow deaf children to retrieve signs using the relevant parameters and,thus, the meaning of the sign in Spanish.} } @inproceedings{chetelat-pele-braffort-2008-sign:lrec, author = {Ch{\'e}telat-Pel{\'e}, Emilie and Braffort, Annelies}, title = {Sign Language Corpus Annotation: toward a new Methodology}, pages = {668--671}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Tapias, Daniel}, booktitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {26}, month = may, year = {2008}, isbn = {978-2-9517408-4-6}, language = {english}, url = {https://aclanthology.org/L08-1468}, doi = {10.63317/39gwhvj26cjy}, abstract = {This paper deals with non manual gestures annotation involved in Sign Language within the context of automatic generation of Sign Language. We will tackle linguistic researches in sign language, present descriptions of non manual gestures and problems lead to movement description. Then, we will propose a new annotation methodology, which allows non manual gestures description. This methodology can describe all Non Manual Gestures with precision, economy and simplicity. It is based on four points: Movement description (instead of position description); Movement decomposition (the diagonal movement is described with horizontal movement and vertical movement separately); Element decomposition (we separate higher eyelid and lower eyelid); Use of a set of symbols rather than words. One symbol can describe many phenomena (with use of colours, height...). First analysis results allow us to define precisely the structure of eye blinking and give the very first ideas for the rules to be designed. All the results must be refined and confirmed by extending the study on the whole corpus. In a second step, our annotation will be used to produce analyses in order to define rules and structure definition of Non Manual Gestures that will be evaluate in LIMSI’s automatic French Sign Language generation system.} } @inproceedings{dreuw-etal-2008-benchmark:lrec, author = {Dreuw, Philippe and Neidle, Carol and Athitsos, Vassilis and Sclaroff, Stan and Ney, Hermann}, title = {Benchmark Databases for Video-Based Automatic Sign Language Recognition}, pages = {1115--1120}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Tapias, Daniel}, booktitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {26}, month = may, year = {2008}, isbn = {978-2-9517408-4-6}, language = {english}, url = {https://aclanthology.org/L08-1469}, doi = {10.63317/4wzouow58zat}, abstract = {A new, linguistically annotated, video database for automatic sign language recognition is presented. The new RWTH-BOSTON-400 corpus, which consists of 843 sentences, several speakers and separate subsets for training, development, and testing is described in detail. For evaluation and benchmarking of automatic sign language recognition, large corpora are needed. Recent research has focused mainly on isolated sign language recognition methods using video sequences that have been recorded under lab conditions using special hardware like data gloves. Such databases have often consisted generally of only one speaker and thus have been speaker-dependent, and have had only small vocabularies. A new database access interface, which was designed and created to provide fast access to the database statistics and content, makes it possible to easily browse and retrieve particular subsets of the video database. Preliminary baseline results on the new corpora are presented. In contradistinction to other research in this area, all databases presented in this paper will be publicly available.} } @inproceedings{bungeroth-etal-2008-atis:lrec, author = {Bungeroth, Jan and Stein, Daniel and Dreuw, Philippe and Ney, Hermann and Morrissey, Sara and Way, Andy and van Zijl, Lynette}, title = {The {ATIS} Sign Language Corpus}, pages = {2943--2946}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Tapias, Daniel}, booktitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {26}, month = may, year = {2008}, isbn = {978-2-9517408-4-6}, language = {english}, url = {https://aclanthology.org/L08-1470}, doi = {10.63317/52zjy2i8c79h}, abstract = {Systems that automatically process sign language rely on appropriate data. We therefore present the ATIS sign language corpus that is based on the domain of air travel information. It is available for five languages, English, German, Irish sign language, German sign language and South African sign language. The corpus can be used for different tasks like automatic statistical translation and automatic sign language recognition and it allows the specific modeling of spatial references in signing space.} } @inproceedings{campr-etal-2008-collection:lrec, author = {Campr, Pavel and Hr{\'u}z, Marek and Trojanov{\'a}, Jana}, title = {Collection and Preprocessing of {C}zech {S}ign {L}anguage Corpus for Sign Language Recognition}, pages = {3175--3178}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Tapias, Daniel}, booktitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {26}, month = may, year = {2008}, isbn = {978-2-9517408-4-6}, language = {english}, url = {https://aclanthology.org/L08-1471}, doi = {10.63317/4r8ddxura727}, abstract = {This paper discusses the design, recording and preprocessing of a Czech sign language corpus. The corpus is intended for training and testing of sign language recognition (SLR) systems. The UWB-07-SLR-P corpus contains video data of 4 signers recorded from 3 different perspectives. Two of the perspectives contain whole body and provide 3D motion data, the third one is focused on signer’s face and provide data for face expression and lip feature extraction. Each signer performed 378 signs with 5 repetitions. The corpus consists of several types of signs: numbers (35 signs), one and two-handed finger alphabet (64), town names (35) and other signs (244). Each sign is stored in a separate AVI file. In total the corpus consists of 21853 video files in total length of 11.1 hours. Additionally each sign is preprocessed and basic features such as 3D hand and head trajectories are available. The corpus is mainly focused on feature extraction and isolated SLR rather than continuous SLR experiments.} } @inproceedings{wittenburg-etal-2006-elan:lrec, author = {Wittenburg, Peter and Brugman, Hennie and Russel, Albert and Klassmann, Alex and Sloetjes, Han}, title = {{ELAN}: a Professional Framework for Multimodality Research}, pages = {1556--1559}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Gangemi, Aldo and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Tapias, Daniel}, booktitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {22--28}, month = may, year = {2006}, isbn = {978-2-9517408-2-2}, language = {english}, url = {https://aclanthology.org/L06-1082}, doi = {10.63317/5pwa5zpssv4z}, abstract = {Utilization of computer tools in linguistic research has gained importance with the maturation of media frameworks for the handling of digital audio and video. The increased use of these tools in gesture, sign language and multimodal interaction studies has led to stronger requirements on the flexibility, the efficiency and in particular the time accuracy of annotation tools. This paper describes the efforts made to make ELAN a tool that meets these requirements, with special attention to the developments in the area of time accuracy. In subsequent sections an overview will be given of other enhancements in the latest versions of ELAN that makes it a useful tool in multimodality research.} } @inproceedings{segouat-etal-2006-sign:lrec, author = {Segouat, J{\'e}r{\'e}mie and Braffort, Annelies and Martin, Emilie}, title = {Sign Language corpus analysis: Synchronisation of linguistic annotation and numerical data}, pages = {1996--1999}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Gangemi, Aldo and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Tapias, Daniel}, booktitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {22--28}, month = may, year = {2006}, isbn = {978-2-9517408-2-2}, language = {english}, url = {https://aclanthology.org/L06-1347}, doi = {10.63317/4z4htio97ebh}, abstract = {This paper presents a study on synchronization of linguistic annotation and numerical data on a video corpus of French Sign Language. We detail the methodology and sketches out the potential observations that can be provided by such a kind of mixed annotation. The corpus is composed of three views: close-up, frontal and top. Some image processing has been performed on each video in order to provide global information on the movement of the signers. That consists of the size and position of a bounding box surrounding the signer. Linguists have studied this corpus and have provided annotations on iconic structures, such as ``personal transfers'' (role shifts). We used an annotation software, ANVIL, to synchronize linguistic annotation and numerical data. This new approach of annotation seems promising for automatic detection of linguistic phenomena, such as classification of the signs according to their size in the signing space, and detection of some iconic structures. Our first results must be consolidated and extended on the whole corpus. The next step will consist of designing automatic processes in order to assist SL annotation.} } @inproceedings{bungeroth-etal-2006-german:lrec, author = {Bungeroth, Jan and Stein, Daniel and Dreuw, Philippe and Zahedi, Morteza and Ney, Hermann}, title = {A {G}erman {S}ign {L}anguage Corpus of the Domain Weather Report}, pages = {2000--2003}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Gangemi, Aldo and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Tapias, Daniel}, booktitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {22--28}, month = may, year = {2006}, isbn = {978-2-9517408-2-2}, language = {english}, url = {https://aclanthology.org/L06-1418}, doi = {10.63317/5hcqquw2odw9}, abstract = {All systems for automatic sign language translation and recognition, in particular statistical systems, rely on adequately sized corpora. For this purpose, we created the Phoenix corpus that is based on German television weather reports translated into German Sign Language. It comes with a rich annotation of the video data, a bilingual text-based sentence corpus and a monolingual German corpus. All systems for automatic sign language translation and recognition, in particular statistical systems, rely on adequately sized corpora. For this purpose, we created the Phoenix corpus that is based on German television weather reports translated into German Sign Language. It comes with a rich annotation of the video data, a bilingual text-based sentence corpus and a monolingual German corpus.} } @inproceedings{suzuki-etal-2006-web:lrec, author = {Suzuki, Emiko and Suzuki, Tomomi and Kakihana, Kyoko}, title = {On the Web Trilingual Sign Language Dictionary to Learn the foreign Sign Language without Learning a Target Spoken Language}, pages = {2307--2310}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Gangemi, Aldo and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Tapias, Daniel}, booktitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Genoa, Italy}, day = {22--28}, month = may, year = {2006}, isbn = {978-2-9517408-2-2}, language = {english}, url = {https://aclanthology.org/L06-1146}, doi = {10.63317/3h96mi36xtww}, abstract = {This paper describes a trilingual sign language dictionary (Japanese Sign Language and American Sign Language, and Korean Sign Language) which helps those who learn each sign language directly from their mother sign language. Our discussion covers two main points. The first describes the necessity of a trilingual dictionary. Since there is no “universal sign language” or real “international sign language” deaf people should learn at least four languages: they want to talk to people whose mother tongue is different from their owns, the mother sign language, the mother spoken language as the first intermediate language, the target spoken language as the second intermediate language, and the sign language in which they want to communicate. Those two spoken languages become language barriers for deaf people and our trilingual dictionary will remove the barrier. The second describes the use of computer. As the use of computers becomes widespread, it is increasingly convenient to study through computer software or Internet facilities. Our WWW dictionary system provides deaf people with an easy means of access using their mother-sign language, which means they don't have to overcome the barrier of learning a foreign spoken language. It also provides a way for people who are going to learn three sign languages to look up new vocabulary. We are further planning to examine how our dictionary system could be used to educate and assist deaf people.} } @inproceedings{braffort-etal-2004-toward:lrec, author = {Braffort, Annelies and Choisier, Annick and Collet, Christophe and Dalle, Patrice and Gianni, Fr{\'e}d{\'e}rick and Lenseigne, Boris and Segouat, J{\'e}r{\'e}mie}, title = {Toward an Annotation Software for Video of Sign Language, Including Image Processing Tools and Signing Space Modelling}, pages = {201--204}, editor = {Lino, Maria Teresa and Xavier, Maria Francisca and Ferreira, F{\'a}tima and Costa, Rute and Silva, Raquel}, booktitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {24--30}, month = may, year = {2004}, isbn = {978-2-9517408-1-5}, language = {english}, url = {https://aclanthology.org/L04-1419}, doi = {10.63317/442zcqrzdvi9}, abstract = {Several French national projects have been achieved last years, allowing linguist and computer scientists working on French Sign Language (FSL) to establish a permanent collaboration. During these projects, several video FSL corpora have been realised. One of the research orientations induced by these projects relates to multi-disciplinary annotation. From the computer scientist's side, the aim is to develop an annotation software integrating different kind of tools based on image processing and 3d modelling that will be used to automatically annotate both lexical and syntactic information. This article presents several of these components. A first version of the annotation software integrating these components is under development.} } @inproceedings{brugman-etal-2004-collaborative:lrec, author = {Brugman, Hennie and Crasborn, Onno and Russel, Albert}, title = {Collaborative Annotation of Sign Language Data with Peer-to-Peer Technology}, pages = {213--216}, editor = {Lino, Maria Teresa and Xavier, Maria Francisca and Ferreira, F{\'a}tima and Costa, Rute and Silva, Raquel}, booktitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Lisbon, Portugal}, day = {24--30}, month = may, year = {2004}, isbn = {978-2-9517408-1-5}, language = {english}, url = {https://aclanthology.org/L04-1280}, doi = {10.63317/3m89b6txpbi8}, abstract = {Collaboration on annotation projects is in practice mostly done by people sharing the same room. However, several models for online cooperative annotation over the internet are possible. This paper explores and evaluates these, and reports on the use of peer-to-peer technology to extend a multimedia annotation tool (ELAN) with functions that support collaborative annotation.} } @inproceedings{wittenburg-etal-2002-multimodal:lrec, author = {Wittenburg, Peter and Levinson, Stephen and Kita, Sotaro and Brugman, Hennie}, title = {Multimodal Annotations in Gesture and Sign Language Studies}, pages = {176--182}, editor = {Rodr{\'i}guez, Manuel Gonz{\'a}lez and Araujo, Carmen Paz Suarez}, booktitle = {3rd International Conference on Language Resources and Evaluation ({LREC} 2002)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Las Palmas, Canary Islands, Spain}, day = {27}, month = may, year = {2002}, language = {english}, url = {https://aclanthology.org/L02-1223}, doi = {10.63317/2iaqjhvw3fot}, abstract = {For multimodal annotations an exhaustive encoding system for gestures was developed to facilitate research. The structural requirements of multimodal annotations were analyzed to develop an Abstract Corpus Model which is the basis for a powerful annotation and exploitation tool for multimedia recordings and the definition of the XML-based EUDICO Annotation Format. Finally, a metadata-based data management environment has been setup to facilitate resource discovery and especially corpus management. Bt means of an appropriate digitization policy and their online availability researchers have been able to build up a large corpus covering gesture and sign language data.} } @inproceedings{suzuki-kakihana-2002-japanese:lrec, author = {Suzuki, Emiko and Kakihana, Kyoko}, title = {{J}apanese and {A}merican {S}ign {L}anguage Dictionary System for {J}apanese and {E}nglish Users}, pages = {677--680}, editor = {Rodr{\'i}guez, Manuel Gonz{\'a}lez and Araujo, Carmen Paz Suarez}, booktitle = {3rd International Conference on Language Resources and Evaluation ({LREC} 2002)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Las Palmas, Canary Islands, Spain}, day = {27}, month = may, year = {2002}, language = {english}, url = {https://aclanthology.org/L02-1332}, doi = {10.63317/2esxhxq7p4ei}, abstract = {We discuss the basic ideas behind a Japanese and American Sign Language Dictionary System for Japanese and English users. Our discussion covers two main points. The first describes the necessity of a bilingual dictionary. Since there is no ``universal sign language'' or real ``international sign language,'' if Deaf people should learn at least three languages: they want to talk to people whose mother tongue is different from their owns, the mother sign language, the mother spoken language as an intermediate language, and the sign language in which they want to communicate. The second describes the use of computer. As the use of computers becomes widespread, it is increasingly convenient to study through computer software or Internet facilities. Our dictionary system provides Deaf people with an easy means of access using their mother-spoken language. It also provides a way for people who are going to learn two sign languages to look up new vocabulary. We are further planning to examine how our system could be used to educate and assist Deaf people.} } @inproceedings{hanke-2002-ilex:lrec, author = {Hanke, Thomas}, title = {i{L}ex - A Tool for Sign Language Lexicography and Corpus Analysis}, pages = {923--926}, editor = {Rodr{\'i}guez, Manuel Gonz{\'a}lez and Araujo, Carmen Paz Suarez}, booktitle = {3rd International Conference on Language Resources and Evaluation ({LREC} 2002)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Las Palmas, Canary Islands, Spain}, day = {27}, month = may, year = {2002}, language = {english}, url = {https://aclanthology.org/L02-1330}, doi = {10.63317/3nb76bqgx946}, abstract = {This paper describes a tool that combines features found in empirical sign language lexicography and in sign language discourse transcription. It supports the user in lexicon building while working on the transcription of a corpus. While it tries to reach a certain level of compatibility with upcoming multimedia annotation tools, it offers a number of unique features considered essential due to the specific nature of sign languages.} } @inproceedings{koizumi-etal-2002-annotated:lrec, author = {Koizumi, Atsuko and Sagawa, Hirohiko and Takeuchi, Masaru}, title = {An Annotated {J}apanese {S}ign {L}anguage Corpus}, pages = {927--930}, editor = {Rodr{\'i}guez, Manuel Gonz{\'a}lez and Araujo, Carmen Paz Suarez}, booktitle = {3rd International Conference on Language Resources and Evaluation ({LREC} 2002)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Las Palmas, Canary Islands, Spain}, day = {27}, month = may, year = {2002}, language = {english}, url = {https://aclanthology.org/L02-1318}, doi = {10.63317/33icn6fm4b8p}, abstract = {Sign language is characterized by its interactivity and multimodality, which cause difficulties in data collection and annotation. To address these difficulties, we have developed a video-based Japanese sign language (JSL) corpus and a corpus tool for annotation and linguistic analysis. As the first step of linguistic annotation, we transcribed manual signs expressing lexical information as well as non-manual signs (NMSs) - including head movements, facial actions, and posture - that are used to express grammatical information. Our purpose is to extract grammatical rules from this corpus for the sign-language translation system underdevelopment. From this viewpoint, we will discuss methods for collecting elicited data, annotation required for grammatical analysis, as well as corpus tool required for annotation and grammatical analysis. As the result of annotating 2800 utterances, we confirmed that there are at least 50 kinds of NMSs in JSL, using head (seven kinds), jaw (six kinds), mouth (18 kinds), cheeks (one kind), eyebrows (four kinds), eyes (seven kinds), eye gaze (two kinds), bydy posture (five kinds). We use this corpus for designing and testing an algorithm and gram- matical rules for the sign-language translation system underdevelopment.} }