Debunking Biases in Attention

Shijing Chen, Usman Naseem, Imran Razzak


Abstract
Despite the remarkable performances in various applications, machine learning (ML) models could potentially discriminate. They may result in biasness in decision-making, leading to an impact negatively on individuals and society. Recently, various methods have been developed to mitigate biasness and achieve significant performance. Attention mechanisms are a fundamental component of many state-of-the-art ML models and may potentially impact the fairness of ML models. However, how they explicitly influence fairness has yet to be thoroughly explored. In this paper, we investigate how different attention mechanisms affect the fairness of ML models, focusing on models used in Natural Language Processing (NLP) models. We evaluate the performance of fairness of several models with and without different attention mechanisms on widely used benchmark datasets. Our results indicate that the majority of attention mechanisms that have been assessed can improve the fairness performance of Bidirectional Gated Recurrent Unit (BiGRU) and Bidirectional Long Short-Term Memory (BiLSTM) in all three datasets regarding religious and gender-sensitive groups, however, with varying degrees of trade-offs in accuracy measures. Our findings highlight the possibility of fairness being affected by adopting specific attention mechanisms in machine learning models for certain datasets
Anthology ID:
2023.trustnlp-1.13
Volume:
Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anaelia Ovalle, Kai-Wei Chang, Ninareh Mehrabi, Yada Pruksachatkun, Aram Galystan, Jwala Dhamala, Apurv Verma, Trista Cao, Anoop Kumar, Rahul Gupta
Venue:
TrustNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
141–150
Language:
URL:
https://aclanthology.org/2023.trustnlp-1.13
DOI:
10.18653/v1/2023.trustnlp-1.13
Bibkey:
Cite (ACL):
Shijing Chen, Usman Naseem, and Imran Razzak. 2023. Debunking Biases in Attention. In Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023), pages 141–150, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Debunking Biases in Attention (Chen et al., TrustNLP 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2023.trustnlp-1.13.pdf
Supplementary material:
 2023.trustnlp-1.13.SupplementaryMaterial.zip
Supplementary material:
 2023.trustnlp-1.13.SupplementaryMaterial.zip