How to measure gender bias in machine translation: Real-world oriented machine translators, multiple reference points

Elsevier, Social Sciences & Humanities Open, Volume 5, Issue 1, 2022, 100239
Anna Farkas, Renáta Németh

In this paper—as a case study—we present a systematic study of gender bias in machine translation with Google Translate. We translated sentences containing names of occupations from Hungarian, a language with gender-neutral pronouns, into English. Our aim was to present a fair measure for bias by comparing the translations to a real-world oriented non-biased machine translator. When assessing bias, we used the following reference points: (1) the distribution of men and women among occupations in both the source and the target language countries, as well as (2) the results of a Hungarian survey that examined if certain jobs are generally perceived as feminine or masculine. We also studied how expanding sentences with adjectives referring to occupations affects the gender of the translated pronouns.

As a result, we found bias against both genders, but biased results against women are much more frequent. Translations are closer to our perception of occupations than to objective occupational statistics. Finally, occupations have a greater effect on translation than adjectives