Grounding Sign Language Representation Learning in Phonology

Toon Vandendriessche, Mathieu De Coster, Joni Dambre


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
Anthology ID:
2026.signlang-1.48
Volume:
Proceedings of the LREC 2026 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Eleni Efthimiou, Stavroula-Evita Fotinea, Thomas Hanke, Julie A. Hochgesang, Johanna Mesch, Marc Schulder
Venues:
SignLang | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
468–476
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-signlang-48
DOI:
10.63317/2kyvv756bfmz
Bibkey:
Cite (ACL):
Toon Vandendriessche, Mathieu De Coster, and Joni Dambre. 2026. Grounding Sign Language Representation Learning in Phonology. In Proceedings of the LREC 2026 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion, pages 468–476, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Grounding Sign Language Representation Learning in Phonology (Vandendriessche et al., SignLang 2026)
Copy Citation: