Identifying and Reducing Gender Bias in Word-Level Language Models

Shikha Bordia, Samuel R. Bowman


Abstract
Many text corpora exhibit socially problematic biases, which can be propagated or amplified in the models trained on such data. For example, doctor cooccurs more frequently with male pronouns than female pronouns. In this study we (i) propose a metric to measure gender bias; (ii) measure bias in a text corpus and the text generated from a recurrent neural network language model trained on the text corpus; (iii) propose a regularization loss term for the language model that minimizes the projection of encoder-trained embeddings onto an embedding subspace that encodes gender; (iv) finally, evaluate efficacy of our proposed method on reducing gender bias. We find this regularization method to be effective in reducing gender bias up to an optimal weight assigned to the loss term, beyond which the model becomes unstable as the perplexity increases. We replicate this study on three training corpora—Penn Treebank, WikiText-2, and CNN/Daily Mail—resulting in similar conclusions.
Anthology ID:
N19-3002
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Sudipta Kar, Farah Nadeem, Laura Burdick, Greg Durrett, Na-Rae Han
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7–15
Language:
URL:
https://aclanthology.org/N19-3002
DOI:
10.18653/v1/N19-3002
Bibkey:
Cite (ACL):
Shikha Bordia and Samuel R. Bowman. 2019. Identifying and Reducing Gender Bias in Word-Level Language Models. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 7–15, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Identifying and Reducing Gender Bias in Word-Level Language Models (Bordia & Bowman, NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-3002.pdf
Presentation:
 N19-3002.Presentation.pdf
Note:
 N19-3002.Note.pdf
Video:
 https://aclanthology.org/N19-3002.mp4
Data
Penn TreebankWikiText-2