@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}, 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{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}, 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{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}, 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{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}, 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{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{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}, 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{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}, 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{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}, 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/} }