Efficiently Exploring Large Language Models for Document-Level Machine Translation with In-context Learning

Menglong Cui, Jiangcun Du, Shaolin Zhu, Deyi Xiong


Abstract
Large language models (LLMs) exhibit outstanding performance in machine translation via in-context learning. In contrast to sentence-level translation, document-level translation (DOCMT) by LLMs based on in-context learning faces two major challenges: firstly, document translations generated by LLMs are often incoherent; secondly, the length of demonstration for in-context learning is usually limited. To address these issues, we propose a Context-Aware Prompting method (CAP), which enables LLMs to generate more accurate, cohesive, and coherent translations via in-context learning. CAP takes into account multi-level attention, selects the most relevant sentences to the current one as context, and then generates a summary from these collected sentences. Subsequently, sentences most similar to the summary are retrieved from the datastore as demonstrations, which effectively guide LLMs in generating cohesive and coherent translations. We conduct extensive experiments across various DOCMT tasks, and the results demonstrate the effectiveness of our approach, particularly in zero pronoun translation (ZPT) and literary translation tasks.
Anthology ID:
2024.findings-acl.646
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10885–10897
Language:
URL:
https://aclanthology.org/2024.findings-acl.646
DOI:
10.18653/v1/2024.findings-acl.646
Bibkey:
Cite (ACL):
Menglong Cui, Jiangcun Du, Shaolin Zhu, and Deyi Xiong. 2024. Efficiently Exploring Large Language Models for Document-Level Machine Translation with In-context Learning. In Findings of the Association for Computational Linguistics: ACL 2024, pages 10885–10897, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Efficiently Exploring Large Language Models for Document-Level Machine Translation with In-context Learning (Cui et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.646.pdf