{"ID":2874075,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.04745","arxiv_id":"2509.04745","title":"Phonological Representation Learning for Isolated Signs Improves Out-of-Vocabulary Generalization","abstract":"Sign language datasets are often not representative in terms of vocabulary, underscoring the need for models that generalize to unseen signs. Vector quantization is a promising approach for learning discrete, token-like representations, but it has not been evaluated whether the learned units capture spurious correlations that hinder out-of-vocabulary performance. This work investigates two phonological inductive biases: Parameter Disentanglement, an architectural bias, and Phonological Semi-Supervision, a regularization technique, to improve isolated sign recognition of known signs and reconstruction quality of unseen signs with a vector-quantized autoencoder. The primary finding is that the learned representations from the proposed model are more effective for one-shot reconstruction of unseen signs and more discriminative for sign identification compared to a controlled baseline. This work provides a quantitative analysis of how explicit, linguistically-motivated biases can improve the generalization of learned representations of sign language.","short_abstract":"Sign language datasets are often not representative in terms of vocabulary, underscoring the need for models that generalize to unseen signs. Vector quantization is a promising approach for learning discrete, token-like representations, but it has not been evaluated whether the learned units capture spurious correlatio...","url_abs":"https://arxiv.org/abs/2509.04745","url_pdf":"https://arxiv.org/pdf/2509.04745v1","authors":"[\"Lee Kezar\",\"Zed Sehyr\",\"Jesse Thomason\"]","published":"2025-09-05T01:55:41Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.CV\"]","methods":"[]","has_code":false}