Challenges in Automated Debiasing for Toxic Language Detection

Xuhui Zhou, Maarten Sap, Swabha Swayamdipta, Yejin Choi, Noah Smith


Abstract
Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently introduced debiasing methods for text classification datasets and models, as applied to toxic language detection. Our focus is on lexical (e.g., swear words, slurs, identity mentions) and dialectal markers (specifically African American English). Our comprehensive experiments establish that existing methods are limited in their ability to prevent biased behavior in current toxicity detectors. We then propose an automatic, dialect-aware data correction method, as a proof-of-concept. Despite the use of synthetic labels, this method reduces dialectal associations with toxicity. Overall, our findings show that debiasing a model trained on biased toxic language data is not as effective as simply relabeling the data to remove existing biases.
Anthology ID:
2021.eacl-main.274
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3143–3155
Language:
URL:
https://aclanthology.org/2021.eacl-main.274
DOI:
10.18653/v1/2021.eacl-main.274
Bibkey:
Cite (ACL):
Xuhui Zhou, Maarten Sap, Swabha Swayamdipta, Yejin Choi, and Noah Smith. 2021. Challenges in Automated Debiasing for Toxic Language Detection. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3143–3155, Online. Association for Computational Linguistics.
Cite (Informal):
Challenges in Automated Debiasing for Toxic Language Detection (Zhou et al., EACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.eacl-main.274.pdf
Code
 XuhuiZhou/Toxic_Debias +  additional community code