Addressing Entity Translation Problem via Translation Difficulty and Context Diversity

Tian Liang, Xing Wang, Mingming Yang, Yujiu Yang, Shuming Shi, Zhaopeng Tu


Abstract
Neural machine translation (NMT) systems often produce inadequate translations for named entities. In this study, we conducted preliminary experiments to examine the factors affecting the translation accuracy of named entities, specifically focusing on their translation difficulty and context diversity. Based on our observations, we propose a novel data augmentation strategy to enhance the accuracy of named entity translation. The main concept behind our approach is to increase both the context diversity and translation probability for the targeted named entity pair. To achieve this, we construct additional samples for named entities that exhibit high translation difficulty or low context diversity and use the augmented training data to re-train the final translation model. Furthermore, we propose an entity-aware machine translation metric that prefers the translation output to generate more accurate named entities. Our experimental results demonstrate significant improvements over the baseline in terms of general translation performance and named entity translation accuracy across various test sets, such as WMT news translation and terminology test sets.
Anthology ID:
2024.findings-acl.691
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:
11628–11638
Language:
URL:
https://aclanthology.org/2024.findings-acl.691
DOI:
10.18653/v1/2024.findings-acl.691
Bibkey:
Cite (ACL):
Tian Liang, Xing Wang, Mingming Yang, Yujiu Yang, Shuming Shi, and Zhaopeng Tu. 2024. Addressing Entity Translation Problem via Translation Difficulty and Context Diversity. In Findings of the Association for Computational Linguistics: ACL 2024, pages 11628–11638, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Addressing Entity Translation Problem via Translation Difficulty and Context Diversity (Liang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.691.pdf