It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution

Understand

This paper treats gender bias latent in word embeddings.

• Previous mitigation attempts rely on the operationalisation of gender bias as a projection over a linear subspace.
• An alternative approach is Counterfactual Data Augmentation (CDA), in which a corpus is duplicated and augmented to remove bias, e.g.
• by swapping all inherently-gendered words in the copy.