Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology
This addresses the issue of gender bias in NLP systems for languages with complex grammar, which is an incremental improvement over existing methods focused on English.
The paper tackles the problem of mitigating gender stereotypes in morphologically rich languages by presenting a novel approach for converting between masculine-inflected and feminine-inflected sentences, achieving F1 scores of 82% and 73% for Spanish and Hebrew and reducing gender stereotyping by a factor of 2.5 on average without sacrificing grammaticality.
Gender stereotypes are manifest in most of the world's languages and are consequently propagated or amplified by NLP systems. Although research has focused on mitigating gender stereotypes in English, the approaches that are commonly employed produce ungrammatical sentences in morphologically rich languages. We present a novel approach for converting between masculine-inflected and feminine-inflected sentences in such languages. For Spanish and Hebrew, our approach achieves F1 scores of 82% and 73% at the level of tags and accuracies of 90% and 87% at the level of forms. By evaluating our approach using four different languages, we show that, on average, it reduces gender stereotyping by a factor of 2.5 without any sacrifice to grammaticality.