Standard debiasing of word embeddings increases the gender bias of a downstream occupation classifier, while a strong debiasing variant that removes the gender subspace from all words reduces bias and preserves accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Debiasing Embeddings for Reduced Gender Bias in Text Classification
Standard debiasing of word embeddings increases the gender bias of a downstream occupation classifier, while a strong debiasing variant that removes the gender subspace from all words reduces bias and preserves accuracy.