AIST AIRC Systems for the WMT 2024 Shared Tasks

Matiss Rikters, Makoto Miwa


Abstract
At WMT 2024 AIST AIRC participated in the General Machine Translation shared task and the Biomedical Translation task. We trained constrained track models for translation between English, German, and Japanese. Before training the final models, we first filtered the parallel data, then performed iterative back-translation as well as parallel data distillation. We experimented with training baseline Transformer models, Mega models, and fine-tuning open-source T5 and Gemma model checkpoints using the filtered parallel data. Our primary submissions contain translations from ensembles of two Mega model checkpoints and our contrastive submissions are generated by our fine-tuned T5 model checkpoints.
Anthology ID:
2024.wmt-1.22
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:
286–291
Language:
URL:
https://aclanthology.org/2024.wmt-1.22
DOI:
10.18653/v1/2024.wmt-1.22
Bibkey:
Cite (ACL):
Matiss Rikters and Makoto Miwa. 2024. AIST AIRC Systems for the WMT 2024 Shared Tasks. In Proceedings of the Ninth Conference on Machine Translation, pages 286–291, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
AIST AIRC Systems for the WMT 2024 Shared Tasks (Rikters & Miwa, WMT 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.wmt-1.22.pdf