@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}, 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{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}, 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{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{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}, 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.} }