@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 = {{European 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.}
}