@inproceedings{bianco-etal-2025-multilingual,
    title = "Multilingual Sign Language Translation with Unified Datasets and Pose-Based Transformers",
    author = "Bianco, Pedro Alejandro Dal  and
      Stanchi, Oscar Agust{\'i}n  and
      Quiroga, Facundo Manuel  and
      Ronchetti, Franco",
    editor = "Hasanuzzaman, Mohammed  and
      Quiroga, Facundo Manuel  and
      Modi, Ashutosh  and
      Kamila, Sabyasachi  and
      Artiaga, Keren  and
      Joshi, Abhinav  and
      Singh, Sanjeet",
    booktitle = "Proceedings of the Workshop on Sign Language Processing (WSLP)",
    month = dec,
    year = "2025",
    address = "IIT Bombay, Mumbai, India (Co-located with IJCNLP{--}AACL 2025)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.wslp-main.5/",
    pages = "27--32",
    ISBN = "979-8-89176-304-3",
    abstract = "Sign languages are highly diverse across countries and regions, yet most Sign Language Translation (SLT) work remains monolingual. We explore a unified, multi-target SLT model trained jointly on four sign languages (German, Greek, Argentinian, Indian) using a standardized data layer. Our model operates on pose keypoints extracted with MediaPipe, yielding a lightweight and dataset-agnostic representation that is less sensitive to backgrounds, clothing, cameras, or signer identity while retaining motion and configuration cues. On RWTH-PHOENIX-Weather 2014T, Greek Sign Language Dataset, LSA-T, and ISLTranslate, naive joint training under a fully shared parameterization performs worse than monolingual baselines; however, a simple two-stage schedule: multilingual pre-training followed by a short language-specific fine-tuning, recovers and surpasses monolingual results on three datasets (PHOENIX14T: $+0.15$ BLEU-4; GSL: $+0.74$; ISL: $+0.10$) while narrowing the gap on the most challenging corpus (LSA-T: $-0.24$ vs. monolingual). Scores span from BLEU-4$\approx 1$ on open-domain news (LSA-T) to $>90$ on constrained curricula (GSL), highlighting the role of dataset complexity. We release our code to facilitate training and evaluation of multilingual SLT models."
}