Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation. (arXiv:2009.09435v3 [cs.LG] UPDATED)

Bolukbasi et al. (2016) presents one of the first gender bias mitigation
techniques for word embeddings. Their method takes pre-trained word embeddings
as input and attempts to isolate a linear subspace that captures most of the
gender bias in the embeddings. As judged by an analogical evaluation task,
their method virtually eliminates gender bias in the embeddings. However, an
implicit and untested assumption of their method is that the bias sub-space is
actually linear. In this work, we generalize their …

arxiv bias gender gender bias hypothesis linear