Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness

Domaine:

natural language processing

Type de record:

paper
Créateur:
SplMenWachsmuth, Henning
Hôte:avatar
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. Accepted to Findings of the Association for Computational Linguistics: ACL 2024

Visit

arxiv.org

Tasks

hate speech detectiontext classification

Tags

Computation and Language

Similaires

Understanding Position Bias Effects on Fairness in Social Multi-Document SummarizationUsing Fairness Models to Improve Equity in Health Delivery Fleet ManagementThe Hrunting of AI: Where and How to Improve English Dialectal FairnessCounterfactual Fairness in Mortgage Lending via Matching and Randomizationjoynaomi81/Fairness-and-Bias-Evaluation-of-Transformer-Models-for-Yoruba-Sentiment-AnalysisData from: Improving access to essential medicines via decision-aware machine learning

Understanding Position Bias Effects on Fairness in Social Multi-Document Summarization

Text summarization models have typically focused on optimizing aspects of quality such as fluency, r

Using Fairness Models to Improve Equity in Health Delivery Fleet Management

Inefficiency and inequity are two challenges that plague humanitarian operations and health delivery

The Hrunting of AI: Where and How to Improve English Dialectal Fairness

It is known that large language models (LLMs) underperform in English dialects, and that improving t

Counterfactual Fairness in Mortgage Lending via Matching and Randomization

Unfairness in mortgage lending has created generational inequality among racial and ethnic groups in

joynaomi81/Fairness-and-Bias-Evaluation-of-Transformer-Models-for-Yoruba-Sentiment-Analysis

Data from: Improving access to essential medicines via decision-aware machine learning

A critical challenge in healthcare systems in Low- and Middle-Income Countries (LMICs) is the effic