Does Context Help Mitigate Gender Bias in Neural Machine Translation?
This work addresses gender bias in machine translation, showing that current context-aware methods are insufficient, which is an incremental step in bias mitigation research.
The study examined whether context-aware models mitigate gender bias in neural machine translation, finding that while they improve translation accuracy for feminine terms, they can still maintain or amplify bias.
Neural Machine Translation models tend to perpetuate gender bias present in their training data distribution. Context-aware models have been previously suggested as a means to mitigate this type of bias. In this work, we examine this claim by analysing in detail the translation of stereotypical professions in English to German, and translation with non-informative context in Basque to Spanish. Our results show that, although context-aware models can significantly enhance translation accuracy for feminine terms, they can still maintain or even amplify gender bias. These results highlight the need for more fine-grained approaches to bias mitigation in Neural Machine Translation.