cs.CLApr 3, 2025

Breaking the Silence: A Dataset and Benchmark for Bangla Text-to-Gloss Translation

Authors: Sharif Mohammad Abdullah, Abhijit Paul, Shubhashis Roy Dipta, Zarif Masud, Shebuti Rayana, Ahmedul Kabir

Organizations: IIT, University of Dhaka, Bangladesh · University of Maryland, Baltimore County, USA · Toronto Metropolitian University, Canada · SUNY, Old Westbury, USA

Abstract

Gloss is a written approximation that bridges Sign Language (SL) and its corresponding spoken language. Despite a deaf and hard-of-hearing population of at least 3 million in Bangladesh, Bangla Sign Language (BdSL) remains largely understudied, with very limited prior work on Bangla text-to-gloss translation and no publicly available parallel dataset at the time of this work. To address this gap, we construct the first publicly available Bangla text-to-gloss dataset, consisting of 1,000 manually annotated and 4,000 synthetically generated Bangla sentence-gloss pairs, along with 159 expert human-annotated pairs used as a test set. Our experimental framework performs a comparative analysis between several fine-tuned open-source models and a leading closed-source LLM to evaluate their performance in low-resource BdSL translation. GPT-5.4 achieves the best automatic metric scores, while open-source models perform competitively despite being much smaller. This work introduces the first publicly available expert-annotated Bangla text-to-gloss dataset, benchmark and trained model for Bangla text-to-gloss translation. It also demonstrates the effectiveness of systematically generated synthetic data for addressing challenges in low-resource sign language translation.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. IsharaBART: An efficient BART-Based Framework for Low-Resource Bangla Sign Language Translation

    Nov 12, 2026Aonmoy Das, Ananna Dev Aishi, Md. Fazlul KaderSign Language TranslationLow-Resource Language Processing

  2. SyriSign: A Parallel Corpus for Arabic Text to Syrian Arabic Sign Language Translation

    Mar 31, 2026Mohammad Amer Khalil, Raghad Nahas, Ahmad Nassar +1Sign Language DatasetsSign Language Translation

  3. Prompting with Sign Parameters for Low-resource Sign Language Instruction Generation

    Aug 22, 2025Md Tariquzzaman, Md Farhan Ishmam, Saiyma Sittul Muna +2VLM EvaluationVision-Language Models