Current State-of-the-Art of Bias Detection and Mitigation in Machine Translation for African and European Languages: a Review

TL;DR

This review examines current bias detection and mitigation techniques in machine translation, highlighting the focus on European and African languages and the need for broader language diversity in research.

Contribution

It provides a comprehensive overview of existing methods and emphasizes the gap in research on less-studied languages, encouraging future work to enhance diversity.

Findings

Most research focuses on a few European languages.

Limited work on African and other less-studied languages.

Potential for expanding bias mitigation to more languages.

Abstract

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.