• Computer Science
  • Published in NAACL-HLT 2019

Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them

@inproceedings{Gonen2019LipstickOA,
  title={Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them},
  author={Hila Gonen and Yoav Goldberg},
  booktitle={NAACL-HLT},
  year={2019}
}
Highlight Information
Word embeddings are widely used in NLP for a vast range of tasks. [...] Key Result We conclude that existing bias removal techniques are insufficient, and should not be trusted for providing gender-neutral modeling.Expand Abstract

Figures and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 60 CITATIONS

Evaluating the Underlying Gender Bias in Contextualized Word Embeddings

VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

A Causal Inference Method for Reducing Gender Bias in Word Embedding Relations

VIEW 8 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

deb2viz: Debiasing gender in word embedding data using subspace visualization

VIEW 5 EXCERPTS
CITES RESULTS & BACKGROUND
HIGHLY INFLUENCED

DOUBLE-HARD DEBIASING: TAILORING WORD EM- BEDDINGS FOR GENDER BIAS MITIGATION

  • 2019
VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Probabilistic Bias Mitigation in Word Embeddings

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Function

VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Algorithmic Fairness

VIEW 1 EXCERPT
CITES BACKGROUND

FILTER CITATIONS BY YEAR

2019
2020

CITATION STATISTICS

  • 7 Highly Influenced Citations