Current State-of-the-Art of Bias Detection and Mitigation in Machine Translation for African and European Languages: a Review
This is an incremental review that identifies gaps in bias research for machine translation, particularly affecting underrepresented language communities.
This review paper analyzed bias detection and mitigation methods in machine translation, focusing on European and African languages, and found that most research concentrates on a few languages while highlighting potential for future work on less investigated languages to increase diversity.
Studying bias detection and mitigation methods in natural language processing and the particular case of machine translation is highly relevant, as societal stereotypes might be reflected or reinforced by these systems. In this paper, we analyze the state-of-the-art with a particular focus on European and African languages. We show how the majority of the work in this field concentrates on few languages, and that there is potential for future research to cover also the less investigated languages to contribute to more diversity in the research field.