Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Mitigating Gender Bias in Natural Language Processing: Literature Review

Tony Sun, Andrew Gaut, Shirlyn Tang, Yuxin Huang, Mai ElSherief, Jieyu Zhao, Diba Mirza, Elizabeth Belding, Kai-Wei Chang, William Yang Wang

TL;DR

This paper discusses gender bias based on four forms of representation bias and analyzes methods recognizing gender bias in NLP, and discusses the advantages and drawbacks of existing gender debiasing methods.

Abstract

As Natural Language Processing (NLP) and Machine Learning (ML) tools rise in popularity, it becomes increasingly vital to recognize the role they play in shaping societal biases and stereotypes. Although NLP models have shown success in modeling various applications, they propagate and may even amplify gender bias found in text corpora. While the study of bias in artificial intelligence is not new, methods to mitigate gender bias in NLP are relatively nascent. In this paper, we review contemporary studies on recognizing and mitigating gender bias in NLP. We discuss gender bias based on four forms of representation bias and analyze methods recognizing gender bias. Furthermore, we discuss the advantages and drawbacks of existing gender debiasing methods. Finally, we discuss future studies for recognizing and mitigating gender bias in NLP.

Mitigating Gender Bias in Natural Language Processing: Literature Review

TL;DR

This paper discusses gender bias based on four forms of representation bias and analyzes methods recognizing gender bias in NLP, and discusses the advantages and drawbacks of existing gender debiasing methods.

Abstract

As Natural Language Processing (NLP) and Machine Learning (ML) tools rise in popularity, it becomes increasingly vital to recognize the role they play in shaping societal biases and stereotypes. Although NLP models have shown success in modeling various applications, they propagate and may even amplify gender bias found in text corpora. While the study of bias in artificial intelligence is not new, methods to mitigate gender bias in NLP are relatively nascent. In this paper, we review contemporary studies on recognizing and mitigating gender bias in NLP. We discuss gender bias based on four forms of representation bias and analyze methods recognizing gender bias. Furthermore, we discuss the advantages and drawbacks of existing gender debiasing methods. Finally, we discuss future studies for recognizing and mitigating gender bias in NLP.

Paper Structure

This paper contains 18 sections, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Observing Gender Bias
  3. Adopting Psychological Tests
  4. Analyzing Gender Sub-space in Embeddings
  5. Measuring Performance Differences Across Genders
  6. Debiasing Methods Using Data Manipulation
  7. Debiasing Training Corpora
  8. Data Augmentation
  9. Gender Tagging
  10. Bias Fine-Tuning
  11. Debiasing Gender in Word Embeddings
  12. Removing Gender Subspace in Word Embeddings
  13. Learning Gender-Neutral Word Embeddings
  14. Debiasing by Adjusting Algorithms
  15. Constraining Predictions
  16. ...and 3 more sections

Figures (2)

  • Figure 1: Observation and evaluation of gender bias in NLP. Bias observation occurs in both the training sets and the test sets specifically for evaluating the gender bias of a given algorithm's predictions. Debiasing gender occurs in both the training set and within the algorithm itself.
  • Figure 2: We project five word2vec embeddings onto the 'he' - 'she' direction before and after neutralizing the gender-neutral words maestro, instructor, and homemaker and equalizing the gender-specific pair businessman and businesswoman (Bolukbasi et al., 2018). For both$x$ and $y$-axes, negative values represent male gender bias and positive values represent female gender bias.