The Role of Protected Class Word Lists in Bias Identification of Contextualized Word Representations

AbstractSystemic bias in word embeddings has been widely reported and studied, and efforts made to debias them; however, new contextualized embeddings such as ELMo and BERT are only now being similarly studied. Standard debiasing methods require heterogeneous lists of target words to identify the “bias subspace”. We show show that using new contextualized word embeddings in conceptor debiasing allows us to more accurately debias word embeddings by breaking target word lists into more homogeneous subsets and then combining (”Or’ing”) the debiasing conceptors of the different subsets.