Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness

TL;DR

This paper proposes a multitask learning approach that models dialects as an auxiliary task to improve fairness and detection of biased language across dialects, demonstrating effectiveness on African-American English dialect.

Contribution

Introducing a multitask learning method that incorporates dialect modeling to mitigate bias and enhance biased language detection in NLP tasks.

Findings

Dialect modeling improves fairness in biased language detection.

Multitask learning achieves state-of-the-art performance.

Method enhances reliability in detecting biased language properties.

Abstract

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.