Gender Bias in Machine Translation

Gender Bias in Machine Translation Beatrice Savoldi1,2, Marco Gaido1,2, Luisa Bentivogli2, Matteo Negri2, Marco Turchi2 1University of Trento, Italy 2Fondazione Bruno Kessler, Italy {bsavoldi,mgaido,bentivo,negri,turchi}@fbk.eu Abstract Machine translation (MT) technology has fa- cilitated our daily tasks by providing acces- sible shortcuts for gathering, processing, and communicating information. However, it can suffer from biases that harm users and society at large. As a relatively new field of inquiry, studies of gender bias in MT still lack cohesion. This advocates for a unified framework to ease future research. To this end, we: i) crit- ically 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. 1 Introduction Interest in understanding, assessing, and mitigat- ing gender bias is steadily growing within the natural language processing (NLP) community, with recent studies showing how gender dispar- ities affect language technologies. Sometimes, for example, coreference resolution systems fail to recognize women doctors (Zhao et al., 2017; Rudinger et al., 2018), image captioning mod- els do not detect women sitting next to a com- puter (Hendricks et al., 2018), and automatic speech recognition works better with male voices (Tatman, 2017). Despite a prior disregard for such phenomena within research agendas (Cislak et al., 2018), it is now widely recognized that NLP tools encode and reflect controversial social asymmetries for many seemingly neutral tasks, machine translation (MT) included. Admittedly, the problem is not new (Frank et al., 2004). A few years ago, Schiebinger (2014) criticized the phenomenon of ‘‘masculine default’’ in MT after running one of her interviews through a commer- cial translation system. In spite of several feminine mentions in the text, she was repeatedly referred to by masculine pronouns. Gender-related con- cerns have also been voiced by online MT users, who noticed how commercial systems entrench social gender expectations, for example, translat- ing engineers as masculine and nurses as feminine (Olson, 2018). With language technologies entering wide- spread use and being deployed at a massive scale, their societal impact has raised concern both within (Hovy and Spruit, 2016; Bender et al., 2021) and outside (Dastin, 2018) the scientific community. To take stock of the situation, Sun et al. (2019) reviewed NLP studies on the topic. However, their survey is based on monolingual applications, whose underlying assumptions and solutions may not be directly applicable to lan- guages other than English (Zhou et al., 2019; Zhao et al., 2020; Takeshita et al., 2020) and cross-lingual settings. Moreover, MT is a multi- faceted task, which requires resolving multiple gender-related subtasks at the same time (e.g., co- reference resolution, named entity recognition). Hence, depending on the languages involved and the factors accounted for, gender bias has been conceptualized differently across studies. To date, gender bias in MT has been tackled by means of a narrow, problem-solving oriented approach. While technical countermeasures are needed, fail- ing to adopt a wider perspective …

Content truncated to 500 words