The SETU-ADAPT Submission for WMT 24 Biomedical Shared Task

Antonio Castaldo, Maria Zafar, Prashanth Nayak, Rejwanul Haque, Andy Way, Johanna Monti


Abstract
This system description paper presents SETU-ADAPT’s submission to the WMT 2024 Biomedical Shared Task, where we participated for the language pairs English-to-French and English-to-German. Our approach focused on fine-tuning Large Language Models, using in-domain and synthetic data, employing different data augmentation and data retrieval strategies. We introduce a novel MT framework, involving three autonomous agents: a Translator Agent, an Evaluator Agent and a Reviewer Agent. We present our findings and report the quality of the outputs.
Anthology ID:
2024.wmt-1.53
Volume:
Proceedings of the Ninth Conference on Machine Translation
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
Venue:
WMT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
647–653
Language:
URL:
https://aclanthology.org/2024.wmt-1.53
DOI:
Bibkey:
Cite (ACL):
Antonio Castaldo, Maria Zafar, Prashanth Nayak, Rejwanul Haque, Andy Way, and Johanna Monti. 2024. The SETU-ADAPT Submission for WMT 24 Biomedical Shared Task. In Proceedings of the Ninth Conference on Machine Translation, pages 647–653, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
The SETU-ADAPT Submission for WMT 24 Biomedical Shared Task (Castaldo et al., WMT 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.wmt-1.53.pdf