<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="manzini-etal-2019-black">
    <titleInfo>
        <title>Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Thomas</namePart>
        <namePart type="family">Manzini</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lim</namePart>
        <namePart type="family">Yao Chong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alan</namePart>
        <namePart type="given">W</namePart>
        <namePart type="family">Black</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yulia</namePart>
        <namePart type="family">Tsvetkov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jill</namePart>
            <namePart type="family">Burstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christy</namePart>
            <namePart type="family">Doran</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Thamar</namePart>
            <namePart type="family">Solorio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Minneapolis, Minnesota</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Online texts - across genres, registers, domains, and styles - are riddled with human stereotypes, expressed in overt or subtle ways. Word embeddings, trained on these texts, perpetuate and amplify these stereotypes, and propagate biases to machine learning models that use word embeddings as features. In this work, we propose a method to debias word embeddings in multiclass settings such as race and religion, extending the work of (Bolukbasi et al., 2016) from the binary setting, such as binary gender. Next, we propose a novel methodology for the evaluation of multiclass debiasing. We demonstrate that our multiclass debiasing is robust and maintains the efficacy in standard NLP tasks.</abstract>
    <identifier type="citekey">manzini-etal-2019-black</identifier>
    <identifier type="doi">10.18653/v1/N19-1062</identifier>
    <location>
        <url>https://aclanthology.org/N19-1062</url>
    </location>
    <part>
        <date>2019-06</date>
        <extent unit="page">
            <start>615</start>
            <end>621</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings
%A Manzini, Thomas
%A Yao Chong, Lim
%A Black, Alan W.
%A Tsvetkov, Yulia
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F manzini-etal-2019-black
%X Online texts - across genres, registers, domains, and styles - are riddled with human stereotypes, expressed in overt or subtle ways. Word embeddings, trained on these texts, perpetuate and amplify these stereotypes, and propagate biases to machine learning models that use word embeddings as features. In this work, we propose a method to debias word embeddings in multiclass settings such as race and religion, extending the work of (Bolukbasi et al., 2016) from the binary setting, such as binary gender. Next, we propose a novel methodology for the evaluation of multiclass debiasing. We demonstrate that our multiclass debiasing is robust and maintains the efficacy in standard NLP tasks.
%R 10.18653/v1/N19-1062
%U https://aclanthology.org/N19-1062
%U https://doi.org/10.18653/v1/N19-1062
%P 615-621

Markdown (Informal)

[Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings](https://aclanthology.org/N19-1062) (Manzini et al., NAACL 2019)

• Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings (Manzini et al., NAACL 2019)

ACL

• Thomas Manzini, Lim Yao Chong, Alan W Black, and Yulia Tsvetkov. 2019. Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 615–621, Minneapolis, Minnesota. Association for Computational Linguistics.