It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution

Rowan Hall Maudslay, Hila Gonen, Ryan Cotterell, Simone Teufel


Abstract
This paper treats gender bias latent in word embeddings. Previous mitigation attempts rely on the operationalisation of gender bias as a projection over a linear subspace. An alternative approach is Counterfactual Data Augmentation (CDA), in which a corpus is duplicated and augmented to remove bias, e.g. by swapping all inherently-gendered words in the copy. We perform an empirical comparison of these approaches on the English Gigaword and Wikipedia, and find that whilst both successfully reduce direct bias and perform well in tasks which quantify embedding quality, CDA variants outperform projection-based methods at the task of drawing non-biased gender analogies by an average of 19% across both corpora. We propose two improvements to CDA: Counterfactual Data Substitution (CDS), a variant of CDA in which potentially biased text is randomly substituted to avoid duplication, and the Names Intervention, a novel name-pairing technique that vastly increases the number of words being treated. CDA/S with the Names Intervention is the only approach which is able to mitigate indirect gender bias: following debiasing, previously biased words are significantly less clustered according to gender (cluster purity is reduced by 49%), thus improving on the state-of-the-art for bias mitigation.
Anthology ID:
D19-1530
Original:
D19-1530v1
Version 2:
D19-1530v2
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5267–5275
Language:
URL:
https://aclanthology.org/D19-1530
DOI:
10.18653/v1/D19-1530
Bibkey:
Cite (ACL):
Rowan Hall Maudslay, Hila Gonen, Ryan Cotterell, and Simone Teufel. 2019. It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5267–5275, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution (Hall Maudslay et al., EMNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/D19-1530.pdf
Attachment:
 D19-1530.Attachment.zip
Supplementary:
 D19-1530.Supplementary.pdf