[1906.00742] Gender-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 those word embeddings. Taking gender-bias as a working example, we propose a debiasing method that preserves non-discriminative gender-related information, while removing stereotypical discriminative gender biases from pre-trained word embeddings. Specifically, we consider four types of information: \emph{feminine}, \emph{masculine}, \emph{gender-neutral} and \emph{stereotypical}, which represent the relationship between gender vs. bias, and propose a debiasing method that (a) preserves the gender-related information in feminine and masculine words, (b) preserves the neutrality in gender-neutral words, and (c) removes the biases from stereotypical words. Experimental results on several previously proposed benchmark datasets show that our proposed method can debias pre-trai...

2 mentions: @kanekokaneko123@Bollegala
Keywords: embedding
Date: 2019/06/05 05:15

Referring Tweets

@kanekokaneko123 ACL2019に採択された @Bollegala 先生との共著の論文とコードです: 論文: https://t.co/zBiKoDbHBX コード: https://t.co/plUqB07gyv
@Bollegala Pre-print for our ACL-19 paper on Gender-preserving debiasing https://t.co/HjrGXX9x3E and code https://t.co/LNfROzbiyA is available #NLProc with @kanekokaneko123

Related Entries

Read more Neural Text Embeddings for Information Retrieval (WSDM 2017)
Read more [DL輪読会]Learning an Embedding Space for Transferable Robot Skills
Read more Variational Autoencoder in Tensorflow - facial expression low dimensional embedding - Machine learni...
Read more A Neural Network in PyTorch for Tabular Data with Categorical Embeddings – Let the Machines Learn
Read more [論文紹介] Field-aware Probabilistic Embedding Neural Network for CTR Prediction [RecSys 2018] / Paper s...