TY - GEN

T1 - Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness

AU - Spliethöver, Maximilian

AU - Menon, Sai Nikhil

AU - Wachsmuth, Henning

N1 - Publisher Copyright: © 2024 Association for Computational Linguistics.

PY - 2024/8

Y1 - 2024/8

N2 - Dialects introduce syntactic and lexical variations in language that occur in regional or social groups. Most NLP methods are not sensitive to such variations. This may lead to unfair behavior of the methods, conveying negative bias towards dialect speakers. While previous work has studied dialect-related fairness for aspects like hate speech, other aspects of biased language, such as lewdness, remain fully unexplored. To fill this gap, we investigate performance disparities between dialects in the detection of five aspects of biased language and how to mitigate them. To alleviate bias, we present a multitask learning approach that models dialect language as an auxiliary task to incorporate syntactic and lexical variations. In our experiments with African-American English dialect, we provide empirical evidence that complementing common learning approaches with dialect modeling improves their fairness. Furthermore, the results suggest that multitask learning achieves state-of-the-art performance and helps to detect properties of biased language more reliably.

AB - Dialects introduce syntactic and lexical variations in language that occur in regional or social groups. Most NLP methods are not sensitive to such variations. This may lead to unfair behavior of the methods, conveying negative bias towards dialect speakers. While previous work has studied dialect-related fairness for aspects like hate speech, other aspects of biased language, such as lewdness, remain fully unexplored. To fill this gap, we investigate performance disparities between dialects in the detection of five aspects of biased language and how to mitigate them. To alleviate bias, we present a multitask learning approach that models dialect language as an auxiliary task to incorporate syntactic and lexical variations. In our experiments with African-American English dialect, we provide empirical evidence that complementing common learning approaches with dialect modeling improves their fairness. Furthermore, the results suggest that multitask learning achieves state-of-the-art performance and helps to detect properties of biased language more reliably.

UR - http://www.scopus.com/inward/record.url?scp=85205286976&partnerID=8YFLogxK

U2 - 10.18653/v1/2024.findings-acl.553

DO - 10.18653/v1/2024.findings-acl.553

M3 - Conference contribution

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 9294

EP - 9313

BT - Findings of the Association for Computational Linguistics ACL 2024

A2 - Ku, Lun-Wei

A2 - Martins, Andre

A2 - Srikumar, Vivek

T2 - Findings of the Association for Computational Linguistics ACL 2024

Y2 - 11 August 2024 through 16 August 2024

ER -