Improving Machine Translation with Large Language Models: A Preliminary Study with Cooperative Decoding

Jiali Zeng, Fandong Meng, Yongjing Yin, Jie Zhou

Abstract
Contemporary translation engines based on the encoder-decoder framework have made significant strides in development.However, the emergence of Large Language Models (LLMs) has disrupted their position by presenting the potential for achieving superior translation quality.To uncover the circumstances in which LLMs excel and explore how their strengths can be harnessed to enhance translation quality,we first conduct a comprehensive analysis to assess the strengths and limitations of various commercial NMT systems and MT-oriented LLMs. Our findings indicate that neither NMT nor MT-oriented LLMs alone can effectively address all the translation issues, but MT-oriented LLMs show promise as a complementary solution to NMT systems.Building upon these insights, we propose Cooperative Decoding (CoDec), which treats NMT systems as a pretranslation model and MT-oriented LLMs as a supplemental solution to handle complex scenarios beyond the capability of NMT alone.Experimental results on the WMT22 test sets and a newly collected test set WebCrawl demonstrate the effectiveness and efficiency of CoDec, highlighting its potential as a robust solution for combining NMT systems with MT-oriented LLMs in the field of machine translation.
Anthology ID:
2024.findings-acl.786
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13275–13288
Language:
URL:
https://aclanthology.org/2024.findings-acl.786
DOI:
10.18653/v1/2024.findings-acl.786
Bibkey:
Cite (ACL):
Jiali Zeng, Fandong Meng, Yongjing Yin, and Jie Zhou. 2024. Improving Machine Translation with Large Language Models: A Preliminary Study with Cooperative Decoding. In Findings of the Association for Computational Linguistics ACL 2024, pages 13275–13288, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
Improving Machine Translation with Large Language Models: A Preliminary Study with Cooperative Decoding (Zeng et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2024.findings-acl.786.pdf
PDF Search