Examining Gender Bias in Languages with Grammatical Gender

Abstract

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.

arXiv comment9 pages, 4 figures. Accepted at EMNLP-IJCNLP 2019 as a long paper

References in corpus (6)

• Semantics derived automatically from language corpora contain human-like biases
• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
• Attenuating Bias in Word Vectors
• Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniques
• Evaluating the Underlying Gender Bias in Contextualized Word Embeddings
• Grammatical gender associations outweigh topical gender bias in crosslinguistic word embeddings

Cited by in corpus (3)

• Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias
• Towards Controllable Biases in Language Generation
• Evaluating Metrics for Bias in Word Embeddings