Gender Bias in Machine Translation

TL;DR

This paper reviews gender bias in machine translation, analyzing its conceptualizations, assessment methods, mitigation strategies, and proposing directions for future research to address societal impacts.

Contribution

It offers a comprehensive review and critique of current approaches to understanding and mitigating gender bias in machine translation.

Findings

Gender bias in MT is complex and lacks a unified framework.

Existing mitigation strategies are varied and need systematic evaluation.

Future research should focus on developing cohesive theoretical models.

Abstract

Machine translation (MT) technology has facilitated our daily tasks by providing accessible shortcuts for gathering, elaborating and communicating information. However, it can suffer from biases that harm users and society at large. As a relatively new field of inquiry, gender bias in MT still lacks internal cohesion, which advocates for a unified framework to ease future research. To this end, we: i) critically review current conceptualizations of bias in light of theoretical insights from related disciplines, ii) summarize previous analyses aimed at assessing gender bias in MT, iii) discuss the mitigating strategies proposed so far, and iv) point toward potential directions for future work.