EMNLP 2021main55 citations
Evaluating Debiasing Techniques for Intersectional Biases
Shivashankar Subramanian, Xudong Han, Timothy Baldwin, Trevor Cohn, Lea Frermann
Abstract
Bias is pervasive for NLP models, motivating the development of automatic debiasing techniques. Evaluation of NLP debiasing methods has largely been limited to binary attributes in isolation, e.g., debiasing with respect to binary gender or race, however many corpora involve multiple such attributes, possibly with higher cardinality. In this paper we argue that a truly fair model must consider ‘gerrymandering’ groups which comprise not only single attributes, but also intersectional groups. We evaluate a form of bias-constrained model which is new to NLP, as well an extension of the iterative nullspace projection technique which can handle multiple identities.
BibTeX
@inproceedings{subramanian-etal-2021-evaluating,
title = "Evaluating Debiasing Techniques for Intersectional Biases",
author = "Subramanian, Shivashankar and
Han, Xudong and
Baldwin, Timothy and
Cohn, Trevor and
Frermann, Lea",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.193/",
doi = "10.18653/v1/2021.emnlp-main.193",
pages = "2492--2498"
}