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 Y. Goldberg},
  booktitle={NAACL-HLT},
  year={2019}
}
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
180 Citations
Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation
  • 11
  • Highly Influenced
  • PDF
Debiasing Embeddings for Reduced Gender Bias in Text Classification
  • 11
  • PDF
MDR Cluster-Debias: A Nonlinear WordEmbedding Debiasing Pipeline
  • Highly Influenced
  • PDF
Extensive study on the underlying gender bias in contextualized word embeddings
  • 1
  • Highly Influenced
Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation
  • 2
  • Highly Influenced
  • PDF
Fair Embedding Engine: A Library for Analyzing and Mitigating Gender Bias in Word Embeddings
  • PDF
Nurse is Closer to Woman than Surgeon? Mitigating Gender-Biased Proximities in Word Embeddings
  • 5
  • PDF
Robustness and Reliability of Gender Bias Assessment in Word Embeddings: The Role of Base Pairs
  • 1
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-8 OF 8 REFERENCES
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
  • 1,026
  • Highly Influential
  • PDF
Learning Gender-Neutral Word Embeddings
  • 134
  • Highly Influential
  • PDF
Word embeddings quantify 100 years of gender and ethnic stereotypes
  • 291
  • PDF
Glove: Global Vectors for Word Representation
  • 17,113
  • PDF
Mitigating Unwanted Biases with Adversarial Learning
  • 309
  • PDF
Semantics derived automatically from language corpora contain human-like biases
  • 818
  • Highly Influential
  • PDF
Visualizing Data using t-SNE
  • 16,259
  • PDF
Efficient Estimation of Word Representations in Vector Space
  • 17,077
  • PDF