Exploring the Traditional NMT Model and Large Language Model for Chat Translation

Jinlong Yang, Hengchao Shang, Daimeng Wei, Jiaxin Guo, Zongyao Li, Zhanglin Wu, Zhiqiang Rao, Shaojun Li, Yuhao Xie, Yuanchang Luo, Zheng Jiawei, Bin Wei, Hao Yang


Abstract
This paper describes the submissions of Huawei Translation Services Center(HW-TSC) to WMT24 chat translation shared task on English↔Germany (en-de) bidirection. The experiments involved fine-tuning models using chat data and exploring various strategies, including Minimum Bayesian Risk (MBR) decoding and self-training. The results show significant performance improvements in certain directions, with the MBR self-training method achieving the best results. The Large Language Model also discusses the challenges and potential avenues for further research in the field of chat translation.
Anthology ID:
2024.wmt-1.105
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:
1031–1037
Language:
URL:
https://aclanthology.org/2024.wmt-1.105
DOI:
Bibkey:
Cite (ACL):
Jinlong Yang, Hengchao Shang, Daimeng Wei, Jiaxin Guo, Zongyao Li, Zhanglin Wu, Zhiqiang Rao, Shaojun Li, Yuhao Xie, Yuanchang Luo, Zheng Jiawei, Bin Wei, and Hao Yang. 2024. Exploring the Traditional NMT Model and Large Language Model for Chat Translation. In Proceedings of the Ninth Conference on Machine Translation, pages 1031–1037, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Exploring the Traditional NMT Model and Large Language Model for Chat Translation (Yang et al., WMT 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.wmt-1.105.pdf