Identifying and Mitigating Gender Bias in Hyperbolic Word Embeddings
Not on the map. Why?
Abstract (arXiv)
Euclidean word embedding models such as GloVe and Word2Vec have been shown to reflect human-like gender biases. In this paper, we extend the study of gender bias to the recently popularized hyperbolic word embeddings. We propose gyrocosine bias, a novel measure for quantifying gender bias in hyperbolic word representations and observe a significant presence of gender bias. To address this problem, we propose Poincar'e Gender Debias (PGD), a novel debiasing procedure for hyperbolic word representations. Experiments on a suit of evaluation tests show that PGD effectively reduces bias while adding a minimal semantic offset.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 13 of its 27 references that are in the map. First posted on arXiv 28 Sep 2021.
Builds on
13 of 27 references.
References · 13
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
- 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
- 2016Semantics derived automatically from language corpora contain human-like biasescited by 901
- 2019Identifying and Reducing Gender Bias in Word-Level Language Modelscited by 214
- 2018Riemannian Adaptive Optimization Methodscited by 194
- 2014SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimationcited by 172
- 2018Learning Gender-Neutral Word Embeddingscited by 169
- 2018Poincar'e GloVe: Hyperbolic Word Embeddingscited by 156
- 2020Geoopt: Riemannian Optimization in PyTorchcited by 114
- 2019It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitutioncited by 103
- 2019Gender-preserving Debiasing for Pre-trained Word Embeddingscited by 61
1 more
Built on by
Citing papers per year: 2022: 2.
2 papers.