Gender Bias in Meta-Embeddings. (arXiv:2205.09867v3 [cs.CL] UPDATED)

Different methods have been proposed to develop meta-embeddings from a given
set of source embeddings. However, the source embeddings can contain unfair
gender-related biases, and how these influence the meta-embeddings has not been
studied yet. We study the gender bias in meta-embeddings created under three
different settings: (1) meta-embedding multiple sources without performing any
debiasing (Multi-Source No-Debiasing), (2) meta-embedding multiple sources
debiased by a single method (Multi-Source Single-Debiasing), and (3)
meta-embedding a single source debiased by different methods (Single-Source
Multi-Debiasing). …

arxiv bias gender gender bias meta