Adversarial Scrubbing of Demographic Information for Text Classification

Somnath Basu Roy Chowdhury, Sayan Ghosh, Yiyuan Li, Junier Oliva, Shashank Srivastava, Snigdha Chaturvedi


Abstract
Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated target task. We aim to scrub such undesirable attributes and learn fair representations while maintaining performance on the target task. In this paper, we present an adversarial learning framework “Adversarial Scrubber” (AdS), to debias contextual representations. We perform theoretical analysis to show that our framework converges without leaking demographic information under certain conditions. We extend previous evaluation techniques by evaluating debiasing performance using Minimum Description Length (MDL) probing. Experimental evaluations on 8 datasets show that AdS generates representations with minimal information about demographic attributes while being maximally informative about the target task.
Anthology ID:
2021.emnlp-main.43
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
550–562
Language:
URL:
https://aclanthology.org/2021.emnlp-main.43
DOI:
10.18653/v1/2021.emnlp-main.43
Bibkey:
Cite (ACL):
Somnath Basu Roy Chowdhury, Sayan Ghosh, Yiyuan Li, Junier Oliva, Shashank Srivastava, and Snigdha Chaturvedi. 2021. Adversarial Scrubbing of Demographic Information for Text Classification. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 550–562, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Adversarial Scrubbing of Demographic Information for Text Classification (Basu Roy Chowdhury et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.43.pdf
Software:
 2021.emnlp-main.43.Software.zip
Video:
 https://aclanthology.org/2021.emnlp-main.43.mp4
Code
 brcsomnath/adversarial-scrubber