Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation
Minwoo Lee, Hyukhun Koh, Kang-il Lee, Dongdong Zhang, Minsung Kim, Kyomin Jung
Abstract
Gender bias is a significant issue in machine translation, leading to ongoing research efforts in developing bias mitigation techniques. However, most works focus on debiasing bilingual models without much consideration for multilingual systems. In this paper, we specifically target the gender bias issue of multilingual machine translation models for unambiguous cases where there is a single correct translation, and propose a bias mitigation method based on a novel approach. Specifically, we propose Gender-Aware Contrastive Learning, GACL, which encodes contextual gender information into the representations of non-explicit gender words. Our method is target language-agnostic and is applicable to pre-trained multilingual machine translation models via fine-tuning. Through multilingual evaluation, we show that our approach improves gender accuracy by a wide margin without hampering translation performance. We also observe that incorporated gender information transfers and benefits other target languages regarding gender accuracy. Finally, we demonstrate that our method is applicable and beneficial to models of various sizes.- Anthology ID:
- 2023.emnlp-main.1046
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 16825–16839
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.1046
- DOI:
- 10.18653/v1/2023.emnlp-main.1046
- Cite (ACL):
- Minwoo Lee, Hyukhun Koh, Kang-il Lee, Dongdong Zhang, Minsung Kim, and Kyomin Jung. 2023. Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 16825–16839, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation (Lee et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2023.emnlp-main.1046.pdf