Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics

Paula Czarnowska, Yogarshi Vyas, Kashif Shah


Abstract
Measuring bias is key for better understanding and addressing unfairness in NLP/ML models. This is often done via fairness metrics, which quantify the differences in a model’s behaviour across a range of demographic groups. In this work, we shed more light on the differences and similarities between the fairness metrics used in NLP. First, we unify a broad range of existing metrics under three generalized fairness metrics, revealing the connections between them. Next, we carry out an extensive empirical comparison of existing metrics and demonstrate that the observed differences in bias measurement can be systematically explained via differences in parameter choices for our generalized metrics.
Anthology ID:
2021.tacl-1.74
Volume:
Transactions of the Association for Computational Linguistics, Volume 9
Month:
Year:
2021
Address:
Cambridge, MA
Editors:
Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
1249–1267
Language:
URL:
https://aclanthology.org/2021.tacl-1.74
DOI:
10.1162/tacl_a_00425
Bibkey:
Cite (ACL):
Paula Czarnowska, Yogarshi Vyas, and Kashif Shah. 2021. Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics. Transactions of the Association for Computational Linguistics, 9:1249–1267.
Cite (Informal):
Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics (Czarnowska et al., TACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.tacl-1.74.pdf
Video:
 https://aclanthology.org/2021.tacl-1.74.mp4