Evaluating the Underlying Gender Bias in Contextualized Word Embeddings
This addresses gender bias in NLP applications, which can perpetuate stereotypes, but the work is incremental as it applies existing measures to a newer embedding type.
The paper tackled the problem of gender bias in contextualized word embeddings, finding that they are less biased than standard embeddings, even when the latter are debiased.
Gender bias is highly impacting natural language processing applications. Word embeddings have clearly been proven both to keep and amplify gender biases that are present in current data sources. Recently, contextualized word embeddings have enhanced previous word embedding techniques by computing word vector representations dependent on the sentence they appear in. In this paper, we study the impact of this conceptual change in the word embedding computation in relation with gender bias. Our analysis includes different measures previously applied in the literature to standard word embeddings. Our findings suggest that contextualized word embeddings are less biased than standard ones even when the latter are debiased.