Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology

Ran Zmigrod, Sabrina J. Mielke, Hanna Wallach, Ryan Cotterell


Abstract
Gender stereotypes are manifest in most of the world’s languages and are consequently propagated or amplified by NLP systems. Although research has focused on mitigating gender stereotypes in English, the approaches that are commonly employed produce ungrammatical sentences in morphologically rich languages. We present a novel approach for converting between masculine-inflected and feminine-inflected sentences in such languages. For Spanish and Hebrew, our approach achieves F1 scores of 82% and 73% at the level of tags and accuracies of 90% and 87% at the level of forms. By evaluating our approach using four different languages, we show that, on average, it reduces gender stereotyping by a factor of 2.5 without any sacrifice to grammaticality.
Anthology ID:
P19-1161
Original:
P19-1161v1
Version 2:
P19-1161v2
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1651–1661
Language:
URL:
https://aclanthology.org/P19-1161
DOI:
10.18653/v1/P19-1161
Bibkey:
Cite (ACL):
Ran Zmigrod, Sabrina J. Mielke, Hanna Wallach, and Ryan Cotterell. 2019. Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1651–1661, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology (Zmigrod et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1161.pdf
Presentation:
 P19-1161.Presentation.pdf
Video:
 https://vimeo.com/384485394