Theories of "Gender" in NLP Bias Research

TL;DR

This paper surveys nearly 200 NLP articles on gender bias, revealing a lack of explicit gender theory, limited inclusivity, and the need for interdisciplinary approaches to improve research practices.

Contribution

It provides a comprehensive analysis of how gender is conceptualized in NLP bias research and offers recommendations for more inclusive and theoretically grounded future work.

Findings

Most articles do not explicitly theorize gender.

Very few consider nonbinary or intersectional gender models.

An increase in acknowledgment of gender's complexity over time.

Abstract

The rise of concern around Natural Language Processing (NLP) technologies containing and perpetuating social biases has led to a rich and rapidly growing area of research. Gender bias is one of the central biases being analyzed, but to date there is no comprehensive analysis of how "gender" is theorized in the field. We survey nearly 200 articles concerning gender bias in NLP to discover how the field conceptualizes gender both explicitly (e.g. through definitions of terms) and implicitly (e.g. through how gender is operationalized in practice). In order to get a better idea of emerging trajectories of thought, we split these articles into two sections by time. We find that the majority of the articles do not make their theorization of gender explicit, even if they clearly define "bias." Almost none use a model of gender that is intersectional or inclusive of nonbinary genders; and many conflate sex characteristics, social gender, and linguistic gender in ways that disregard the existence and experience of trans, nonbinary, and intersex people. There is an increase between the two time-sections in statements acknowledging that gender is a complicated reality, however, very few articles manage to put this acknowledgment into practice. In addition to analyzing these findings, we provide specific recommendations to facilitate interdisciplinary work, and to incorporate theory and methodology from Gender Studies. Our hope is that this will produce more inclusive gender bias research in NLP.