Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniques

Abstract

Neural machine translation has significantly pushed forward the quality of the field. However, there are remaining big issues with the output translations and one of them is fairness. Neural models are trained on large text corpora which contain biases and stereotypes. As a consequence, models inherit these social biases. Recent methods have shown results in reducing gender bias in other natural language processing tools such as word embeddings. We take advantage of the fact that word embeddings are used in neural machine translation to propose a method to equalize gender biases in neural machine translation using these representations. Specifically, we propose, experiment and analyze the integration of two debiasing techniques over GloVe embeddings in the Transformer translation architecture. We evaluate our proposed system on the WMT English-Spanish benchmark task, showing gains up to one BLEU point. As for the gender bias evaluation, we generate a test set of occupations and we show that our proposed system learns to equalize existing biases from the baseline system.

arXiv commentThis paper has been accepted for publication at the 1st ACL Workshop on Gender Bias for Natural Language Processing (2019)

References in corpus (5)

• Efficient Estimation of Word Representations in Vector Space
• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
• Getting Gender Right in Neural Machine Translation
• Assessing Gender Bias in Machine Translation -- A Case Study with Google Translate
• Judging a Book by its Description : Analyzing Gender Stereotypes in the Man Bookers Prize Winning Fiction

Cited by in corpus (3)

• Gender Bias in Contextualized Word Embeddings
• Man is to Person as Woman is to Location: Measuring Gender Bias in Named Entity Recognition
• Examining Gender Bias in Languages with Grammatical Gender