Theories of "Sexuality" in Natural Language Processing Bias Research

TL;DR

This paper analyzes how NLP models encode and represent queer sexualities, revealing a lack of clear definitions and conflation with gender, and offers recommendations for more inclusive bias research.

Contribution

It provides a systematic review of 55 studies on sexuality bias in NLP, highlighting gaps and proposing interdisciplinary, community-engaged approaches.

Findings

Sexuality is often ambiguously defined in NLP bias research.

Methods frequently conflate gender and sexual identities.

Recommendations include engaging queer communities and interdisciplinary literature.

Abstract

In recent years, significant advancements in the field of Natural Language Processing (NLP) have positioned commercialized language models as wide-reaching, highly useful tools. In tandem, there has been an explosion of multidisciplinary research examining how NLP tasks reflect, perpetuate, and amplify social biases such as gender and racial bias. A significant gap in this scholarship is a detailed analysis of how queer sexualities are encoded and (mis)represented by both NLP systems and practitioners. Following previous work in the field of AI fairness, we document how sexuality is defined and operationalized via a survey and analysis of 55 articles that quantify sexuality-based NLP bias. We find that sexuality is not clearly defined in a majority of the literature surveyed, indicating a reliance on assumed or normative conceptions of sexual/romantic practices and identities. Further, we find that methods for extracting biased outputs from NLP technologies often conflate gender and sexual identities, leading to monolithic conceptions of queerness and thus improper quantifications of bias. With the goal of improving sexuality-based NLP bias analyses, we conclude with recommendations that encourage more thorough engagement with both queer communities and interdisciplinary literature.