Debiasing Word Embeddings is a computational methodology within natural language processing that identifies and mitigates unintended biases in distributed word representations by modifying their vector space geometry while preserving semantic relationships.
52
Publications
4K
Citations
172
Authors
58
Institutions
Publications per year
2017–2026
51
Parents
Publications
52
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
Tolga Bolukbasi, Kai-Wei Chang, James Zou et al. · arXiv (Cornell University) · 2016 · 1.4K citations · Full text
Towards Debiasing Sentence Representations
Paul Pu Liang, Irene Li, Emily Zheng et al. · 2020 · 151 citations · Full text
1–5 of 52
Authors
172
- MK
5
h-index
- DB
5
h-index
- MR
4
h-index
- AT
3
h-index
- XR
2
h-index
1–5 of 172
Institutions
58
Carnegie Mellon University
Pittsburgh, United States
5 h-index
16 publications
1.5K citations
Vector Institute
Toronto, Canada
5 h-index
15 publications
862 citations
University of Liverpool
Liverpool, United Kingdom
4 h-index
6 publications
346 citations
Tokyo Metropolitan University
Tokyo, Japan
4 h-index
6 publications
346 citations
Universitat Politècnica de Catalunya
Barcelona, Spain
3 h-index
8 publications
814 citations
Amazon (United States)
Seattle, United States
3 h-index
9 publications
283 citations
University of Toronto
Toronto, Canada
3 h-index
10 publications
786 citations
Microsoft (United States)
Redmond, United States
3 h-index
6 publications
5.5K citations
1–8 of 58
Venues
- arXiv (Cornell University)
Repository · 16 publications · 2.1K citations
12
h-index
- Proceedings of the AAAI Conference on Artificial Intelligence
Conference · 4 publications · 145 citations
4
h-index
- Natural Language Engineering
1 publications · 14 citations
1
h-index
- DSpace repository (University of Tartu)
Repository · 1 publications · 12 citations
1
h-index
- Expert Systems with Applications
1 publications · 67 citations
1
h-index
1–5