mlsanityData to 14 Oct 2026

Debiasing Embeddings for Reduced Gender Bias in Text Classification

arXiv 1908.02810 ↗First posted 7 Aug 2019cs.LG cs.CL stat.MLcited by 19

Not on the map. Why?

Abstract (arXiv)

(Bolukbasi et al., 2016) demonstrated that pretrained word embeddings can inherit gender bias from the data they were trained on. We investigate how this bias affects downstream classification tasks, using the case study of occupation classification (De-Arteaga et al.,2019). We show that traditional techniques for debiasing embeddings can actually worsen the bias of the downstream classifier by providing a less noisy channel for communicating gender information. With a relatively minor adjustment, however, we show how these same techniques can be used to simultaneously reduce bias and maintain high classification accuracy.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 8; 2023: 5; 2024: 3.

19 papers.

Sort:

  1. 2021A Survey on Gender Bias in Natural Language Processingcited by 89
  2. 2021Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metricscited by 83
  3. 2022Theories of "Gender" in NLP Bias Researchcited by 62
  4. 2022Choose Your Lenses: Flaws in Gender Bias Evaluationcited by 29
  5. 2023Sociodemographic Bias in Language Models: A Survey and Forward Pathcited by 28
  6. 2022Domain Adaptation meets Individual Fairness. And they get alongcited by 13
  7. 2021Individually Fair Gradient Boostingcited by 12
  8. 2023How Far Can It Go?: On Intrinsic Gender Bias Mitigation for Text Classificationcited by 10
  9. 2023In the Name of Fairness: Assessing the Bias in Clinical Record De-identificationcited by 9
  10. 2022What Changed? Investigating Debiasing Methods using Causal Mediation Analysiscited by 7
  11. 2023Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairnesscited by 7
  12. 2022Toward Understanding Bias Correlations for Mitigation in NLPcited by 5
7 more
  1. 2024GECOBench: A Gender-Controlled Text Dataset and Benchmark for Quantifying Biases in Explanationscited by 5
  2. 2022Counterfactual Multi-Token Fairness in Text Classificationcited by 3
  3. 2022Assessing the Impact of Sequence Length Learning on Classification Tasks for Transformer Encoder Modelscited by 3
  4. 2022A methodology to characterize bias and harmful stereotypes in natural language processing in Latin Americacited by 2
  5. 2023Do Not Harm Protected Groups in Debiasing Language Representation Modelscited by 0
  6. 2024Revisiting The Classics: A Study on Identifying and Rectifying Gender Stereotypes in Rhymes and Poemscited by 0
  7. 2024On Debiasing Text Embeddings Through Context Injectioncited by 0