Boston University Libraries OpenBU
    JavaScript is disabled for your browser. Some features of this site may not work without it.
    View Item 
    •   OpenBU
    • BU Open Access Articles
    • BU Open Access Articles
    • View Item
    •   OpenBU
    • BU Open Access Articles
    • BU Open Access Articles
    • View Item

    Man is to computer programmer as woman is to homemaker? debiasing word embeddings

    Thumbnail
    Date Issued
    2016
    Author(s)
    Bolukbasi, Tolga
    Chang, Kai-Wei
    Zou, James Y.
    Saligrama, Venkatesh
    Kalai, Adam T.
    Share to FacebookShare to TwitterShare by Email
    Export Citation
    Download to BibTex
    Download to EndNote/RefMan (RIS)
    Metadata
    Show full item record
    Permanent Link
    https://hdl.handle.net/2144/37516
    Citation (published version)
    Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, Adam T Kalai. 2016. "Man is to computer programmer as woman is to homemaker? debiasing word embeddings." Advances in Neural Information Processing Systems, pp. 4349 - 4357.
    Abstract
    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.
    Collections
    • ENG: Electrical and Computer Engineering: Scholarly Papers [265]
    • BU Open Access Articles [3866]


    Boston University
    Contact Us | Send Feedback | Help
     

     

    Browse

    All of OpenBUCommunities & CollectionsIssue DateAuthorsTitlesSubjectsThis CollectionIssue DateAuthorsTitlesSubjects

    Deposit Materials

    LoginNon-BU Registration

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    Boston University
    Contact Us | Send Feedback | Help