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.
@article{arxiv.2310.09946,
title = {UvA-MT's Participation in the WMT23 General Translation Shared Task},
author = {Di Wu and Shaomu Tan and David Stap and Ali Araabi and Christof Monz},
journal= {arXiv preprint arXiv:2310.09946},
year = {2023}
}
Comments
This paper has been accepted by the WMT2023 Conference