Measuring and Mitigating Name Biases in Neural Machine Translation

Jun Wang, Benjamin Rubinstein, Trevor Cohn


Abstract
Neural Machine Translation (NMT) systems exhibit problematic biases, such as stereotypical gender bias in the translation of occupation terms into languages with grammatical gender. In this paper we describe a new source of bias prevalent in NMT systems, relating to translations of sentences containing person names. To correctly translate such sentences, a NMT system needs to determine the gender of the name. We show that leading systems are particularly poor at this task, especially for female given names. This bias is deeper than given name gender: we show that the translation of terms with ambiguous sentiment can also be affected by person names, and the same holds true for proper nouns denoting race. To mitigate these biases we propose a simple but effective data augmentation method based on randomly switching entities during translation, which effectively eliminates the problem without any effect on translation quality.
Anthology ID:
2022.acl-long.184
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2576–2590
Language:
URL:
https://aclanthology.org/2022.acl-long.184
DOI:
10.18653/v1/2022.acl-long.184
Bibkey:
Cite (ACL):
Jun Wang, Benjamin Rubinstein, and Trevor Cohn. 2022. Measuring and Mitigating Name Biases in Neural Machine Translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2576–2590, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Measuring and Mitigating Name Biases in Neural Machine Translation (Wang et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/2022.acl-long.184.pdf