Examining Gender Bias in Languages with Grammatical Gender
This addresses bias in non-English languages, an incremental step beyond prior English-focused work.
The paper tackled gender bias in word embeddings for languages with grammatical gender, proposing new evaluation metrics and a mitigation approach that reduced bias while preserving embedding utility across monolingual and bilingual settings.
Recent studies have shown that word embeddings exhibit gender bias inherited from the training corpora. However, most studies to date have focused on quantifying and mitigating such bias only in English. These analyses cannot be directly extended to languages that exhibit morphological agreement on gender, such as Spanish and French. In this paper, we propose new metrics for evaluating gender bias in word embeddings of these languages and further demonstrate evidence of gender bias in bilingual embeddings which align these languages with English. Finally, we extend an existing approach to mitigate gender bias in word embeddings under both monolingual and bilingual settings. Experiments on modified Word Embedding Association Test, word similarity, word translation, and word pair translation tasks show that the proposed approaches effectively reduce the gender bias while preserving the utility of the embeddings.