Neutralizing Gender Bias in Word Embedding with Latent Disentanglement and Counterfactual Generation
arXiv:2004.03133
Abstract
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 downstream tasks. Whereas the previous methods project word embeddings into a linear subspace for debiasing, we introduce a \textit{Latent Disentanglement} method with a siamese auto-encoder structure with an adapted gradient reversal layer. Our structure enables the separation of the semantic latent information and gender latent information of given word into the disjoint latent dimensions. Afterwards, we introduce a \textit{Counterfactual Generation} to convert the gender information of words, so the original and the modified embeddings can produce a gender-neutralized word embedding after geometric alignment regularization, without loss of semantic information. From the various quantitative and qualitative debiasing experiments, our method shows to be better than existing debiasing methods in debiasing word embeddings. In addition, Our method shows the ability to preserve semantic information during debiasing by minimizing the semantic information losses for extrinsic NLP downstream tasks.
arXiv commentFindings of EMNLP2020
References in corpus (9)
- Efficient Estimation of Word Representations in Vector Space
- Distributed Representations of Words and Phrases and their Compositionality
- Semantics derived automatically from language corpora contain human-like biases
- Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
- Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes
- Enriching Word Vectors with Subword Information
- Attenuating Bias in Word Vectors
- Gender-preserving Debiasing for Pre-trained Word Embeddings
- Understanding Undesirable Word Embedding Associations