Learning Gender-Neutral Word Embeddings

Jieyu Zhao, Yichao Zhou, Zeyu Li, Wei Wang, and Kai-Wei Chang, in EMNLP (short), 2018.

Code

Download the full text

Abstract

Word embeddings have become a fundamental component in a wide range of Natu-ral Language Processing (NLP) applications.However, these word embeddings trained onhuman-generated corpora inherit strong gen-der stereotypes that reflect social constructs.In this paper, we propose a novel word em-bedding model, De-GloVe, that preserves gen-der information in certain dimensions of wordvectors while compelling other dimensions tobe free of gender influence. Quantitative andqualitative experiments demonstrate that De-GloVe successfully isolates gender informa-tion without sacrificing the functionality of theembedding model.

Source Code

Bib Entry

@inproceedings{zhao2018learning,
  author = {Zhao, Jieyu and Zhou, Yichao and Li, Zeyu and Wang, Wei and Chang, Kai-Wei},
  title = {Learning Gender-Neutral Word Embeddings},
  booktitle = {EMNLP (short)},
  year = {2018}
}

Related Publications

Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal, ACL Finding, 2022
Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies, EMNLP, 2021
Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer, ACL, 2020
Examining Gender Bias in Languages with Grammatical Gender, EMNLP, 2019
Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations, ICCV, 2019
Gender Bias in Contextualized Word Embeddings, NAACL (short), 2019
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings, NeurIPS, 2016