WMT 2025 CreoleMT Systems Description : Martinican Creole and French

Ludovic Mompelat


Abstract
This paper describes our submissions to the constrained subtask of the WMT25 Creole Machine Translation shared task. We participated with a bidirectional Martinican Creole – French system. Our work explores training-time strategies tailored for low-resource MT, including LoRA fine-tuning, curriculum sampling, gradual unfreezing, and multitask learning. We report competitive results against the baseline on both translation directions.
Anthology ID:
2025.wmt-1.94
Volume:
Proceedings of the Tenth Conference on Machine Translation
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
Venue:
WMT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1198–1200
Language:
URL:
https://preview.aclanthology.org/ingest-emnlp/2025.wmt-1.94/
DOI:
Bibkey:
Cite (ACL):
Ludovic Mompelat. 2025. WMT 2025 CreoleMT Systems Description : Martinican Creole and French. In Proceedings of the Tenth Conference on Machine Translation, pages 1198–1200, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
WMT 2025 CreoleMT Systems Description : Martinican Creole and French (Mompelat, WMT 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-emnlp/2025.wmt-1.94.pdf