Debiasing Embeddings for Reduced Gender Bias in Text Classification
(Bolukbasi et al., 2016) demonstrated that pretrained word embeddings can inherit gender bias from the data they were trained on. We investigate how this bias affects downstream classification tasks, using the case study of occupation classification (De-Arteaga et al.,2019). We show that traditional techniques for debiasing embeddings can actually worsen the bias of the downstream classifier by providing a less noisy channel for communicating gender information. With a relatively minor adjustment, however, we show how these same techniques can be used to simultaneously reduce bias and maintain high classification accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral Classificationtext-classificationText ClassificationWord EmbeddingsSimilar Papers 제목 키워드 기반
Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them
Word embeddings are widely used in NLP for a vast range of tasks. It was shown that word embeddings derived from text corpora reflect gender biases in society. This phenomenon is pervasive and consistent across different…
Word EmbeddingsGender-preserving Debiasing for Pre-trained Word Embeddings
Word embeddings learnt from massive text collections have demonstrated significant levels of discriminative biases such as gender, racial or ethnic biases, which in turn bias the down-stream NLP applications that use tho…
Word EmbeddingsGender Bias in Meta-Embeddings
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 …
Conceptor Debiasing of Word Representations Evaluated on WEAT
Bias in word embeddings such as Word2Vec has been widely investigated, and many efforts made to remove such bias. We show how to use conceptors debiasing to post-process both traditional and contextualized word embedding…
Word EmbeddingsNeutralizing Gender Bias in Word Embedding with Latent Disentanglement and Counterfactual Generation
Recent research demonstrates that word embeddings, trained on the human-generated corpus, have strong gender biases in embedding spaces, and these biases can result in the discriminative results from the various downstre…
counterfactualDisentanglementSentiment AnalysisWord Embeddings