Abstract
This paper describes the UvA-MT’s submission to the WMT 2023 shared task on general machine translation. We participate in the constrained track in two directions: English ↔ Hebrew. In this competition, we show that by using one model to handle bidirectional tasks, as a minimal setting of Multilingual Machine Translation (MMT), it is possible to achieve comparable results with that of traditional bilingual translation for both directions. By including effective strategies, like back-translation, re-parameterized embedding table, and task-oriented fine-tuning, we obtained competitive final results in the automatic evaluation for both English → Hebrew and Hebrew → English directions.- Anthology ID:
- 2023.wmt-1.17
- 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:
- 175–180
- Language:
- URL:
- https://aclanthology.org/2023.wmt-1.17
- DOI:
- 10.18653/v1/2023.wmt-1.17
- Cite (ACL):
- Di Wu, Shaomu Tan, David Stap, Ali Araabi, and Christof Monz. 2023. UvA-MT’s Participation in the WMT 2023 General Translation Shared Task. In Proceedings of the Eighth Conference on Machine Translation, pages 175–180, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- UvA-MT’s Participation in the WMT 2023 General Translation Shared Task (Wu et al., WMT 2023)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2023.wmt-1.17.pdf