Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings

By Tolga Bolukbasi, Kai-Wei Chang, James Y. Zou, Venkatesh Saligrama, Adam Tauman Kalai. 2016

3,784 citations recorded by the source corpus.

The blind application of machine learning runs the risk of amplifying biases present in data. Such a danger is facing us with word embedding, a popular framework to represent text data as vectors which has been used in many machine learning and natural language processing tasks. We show that even word embeddings trained on Google News articles exhibit female/male gender stereotypes to a disturbing extent. This raises concerns because their widespread use, as we describe, often tends to amplify these biases. Geometrically, gender bias is first shown to be captured by a direction in the word embedding. Second, gender neutral words are shown to be linearly separable from gender definition words in the word embedding. Using these properties, we provide a methodology for modifying an embedding to remove gender stereotypes, such as the association between the words receptionist and female, while maintaining desired associations such as between the words queen and female. Using crowd-worker evaluation as well as standard benchmarks, we empirically demonstrate that our algorithms significantly reduce gender bias in embeddings while preserving the its useful properties such as the ability to cluster related concepts and to solve analogy tasks. The resulting embeddings can be used in applications without amplifying gender bias.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Percy Liang
  3. Luke S. Zettlemoyer
  4. Yejin Choi
  5. Jianfeng Gao
  6. Noah A. Smith
  7. Graham Neubig
  8. Yoshua Bengio

In Representation & Self-Supervised Learning

  1. Yoshua Bengio
  2. Ivan Vulic
  3. Yoav Goldberg
  4. Samuel R. Bowman
  5. Ruslan Salakhutdinov
  6. Yonatan Belinkov
  7. Sebastian Ruder
  8. Mohit Bansal

In Safety, Robustness & Interpretability

  1. Adina Williams
  2. Kai-Wei Chang
  3. Yulia Tsvetkov
  4. Eric Michael Smith
  5. Sunipa Dev
  6. Dirk Hovy
  7. Emily Sheng
  8. Isabelle Augenstein

Citations in the corpus