OPUS-CAT Terminology Systems for the WMT23 Terminology Shared Task

Tommi Nieminen


Abstract
This paper describes the submission of the OPUS-CAT project to the WMT 2023 terminology shared task. We trained systems for all three language pairs included in the task. All systems were trained using the same training pipeline with identical methods. Support for terminology was implemented by using the currently popular method of annotating source language terms in the training data with the corresponding target language terms.
Anthology ID:
2023.wmt-1.83
Volume:
Proceedings of the Eighth Conference on Machine Translation
Month:
December
Year:
2023
Address:
Singapore
Editors:
Philipp Koehn, Barry Haddow, Tom Kocmi, Christof Monz
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
912–918
Language:
URL:
https://aclanthology.org/2023.wmt-1.83
DOI:
10.18653/v1/2023.wmt-1.83
Bibkey:
Cite (ACL):
Tommi Nieminen. 2023. OPUS-CAT Terminology Systems for the WMT23 Terminology Shared Task. In Proceedings of the Eighth Conference on Machine Translation, pages 912–918, Singapore. Association for Computational Linguistics.
Cite (Informal):
OPUS-CAT Terminology Systems for the WMT23 Terminology Shared Task (Nieminen, WMT 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.wmt-1.83.pdf