Gender Bias in Machine Translation
This work addresses gender bias in machine translation, which can harm users and society, but it is incremental as it synthesizes prior research rather than introducing new methods or results.
The paper tackles the problem of gender bias in machine translation by reviewing existing conceptualizations, analyses, and mitigation strategies, and proposes a unified framework to guide future research in this emerging field.
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.