Controlling gender equality with shallow NLP techniques

Carl, Michaël; Garnier, Simon; Haller, Johann; Altmayer, A.; Miemietz, Bärbel

doi:10.3115/1220355.1220473

Cited by 6 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A common phenomenon leading to gender bias is a generic masculine pronoun which arises when the masculine form is taken as the generic form to designate all persons of any gender. This is especially the case in the gendered languages [Carl et al 2004]. Generic masculine poses a challenge in text interpretation since it is unclear if a given person denotation refers to a particular person or a generic form to describe all people in a specific group.…”

Section: Detecting Gender Bias In Methodsmentioning

confidence: 99%

A Survey on Gender Bias in Natural Language Processing

Stanczak¹,

Augenstein²

2021

Preprint

View full text Add to dashboard Cite

Language can be used as a means of reproducing and enforcing harmful stereotypes and biases and has been analysed as such in numerous research. In this paper, we present a survey of 304 papers on gender bias in natural language processing. We analyse definitions of gender and its categories within social sciences and connect them to formal definitions of gender bias in NLP research. We survey lexica and datasets applied in research on gender bias and then compare and contrast approaches to detecting and mitigating gender bias. We find that research on gender bias suffers from four core limitations. 1) Most research treats gender as a binary variable neglecting its fluidity and continuity. 2) Most of the work has been conducted in monolingual setups for English or other high-resource languages. 3) Despite a myriad of papers on gender bias in NLP methods, we find that most of the newly developed algorithms do not test their models for bias and disregard possible ethical considerations of their work. 4) Finally, methodologies developed in this line of research are fundamentally flawed covering very limited definitions of gender bias and lacking evaluation baselines and pipelines. We see overcoming these limitations as a necessary development in future research.

show abstract

Section: Detecting Gender Bias In Methodsmentioning

confidence: 99%