Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens

TL;DR

This paper investigates how NLP systems, specifically a large-scale BERT model, can perpetuate ableist bias and intersect with other forms of discrimination like gender and race, highlighting the need for more inclusive AI design.

Contribution

It provides the first detailed analysis of ableist bias in NLP systems through an intersectional lens, revealing complex discrimination patterns.

Findings

NLP models can disadvantage people with disabilities.

Ableist bias intersects with gender and race biases.

Statistically significant evidence of discrimination in word predictions.

Abstract

Much of the world's population experiences some form of disability during their lifetime. Caution must be exercised while designing natural language processing (NLP) systems to prevent systems from inadvertently perpetuating ableist bias against people with disabilities, i.e., prejudice that favors those with typical abilities. We report on various analyses based on word predictions of a large-scale BERT language model. Statistically significant results demonstrate that people with disabilities can be disadvantaged. Findings also explore overlapping forms of discrimination related to interconnected gender and race identities.