Mitigating Gender Bias Amplification in Distribution by Posterior Regularization

Shengyu Jia, Tao Meng, Jieyu Zhao, Kai-Wei Chang


Abstract
Advanced machine learning techniques have boosted the performance of natural language processing. Nevertheless, recent studies, e.g., (CITATION) show that these techniques inadvertently capture the societal bias hidden in the corpus and further amplify it. However, their analysis is conducted only on models’ top predictions. In this paper, we investigate the gender bias amplification issue from the distribution perspective and demonstrate that the bias is amplified in the view of predicted probability distribution over labels. We further propose a bias mitigation approach based on posterior regularization. With little performance loss, our method can almost remove the bias amplification in the distribution. Our study sheds the light on understanding the bias amplification.
Anthology ID:
2020.acl-main.264
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2936–2942
Language:
URL:
https://aclanthology.org/2020.acl-main.264
DOI:
10.18653/v1/2020.acl-main.264
Bibkey:
Cite (ACL):
Shengyu Jia, Tao Meng, Jieyu Zhao, and Kai-Wei Chang. 2020. Mitigating Gender Bias Amplification in Distribution by Posterior Regularization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2936–2942, Online. Association for Computational Linguistics.
Cite (Informal):
Mitigating Gender Bias Amplification in Distribution by Posterior Regularization (Jia et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2020.acl-main.264.pdf
Video:
 http://slideslive.com/38928917
Code
 uclanlp/reducingbias