<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karve-etal-2019-conceptor">
    <titleInfo>
        <title>Conceptor Debiasing of Word Representations Evaluated on WEAT</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Saket</namePart>
        <namePart type="family">Karve</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lyle</namePart>
        <namePart type="family">Ungar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">João</namePart>
        <namePart type="family">Sedoc</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on Gender Bias in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marta</namePart>
            <namePart type="given">R</namePart>
            <namePart type="family">Costa-jussà</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christian</namePart>
            <namePart type="family">Hardmeier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Will</namePart>
            <namePart type="family">Radford</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kellie</namePart>
            <namePart type="family">Webster</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Bias in word representations, such as Word2Vec, has been widely reported and investigated, and efforts made to debias them. We apply the debiasing conceptor for post-processing both traditional and contextualized word embeddings. Our method can simultaneously remove racial and gender biases from word representations. Unlike standard debiasing methods, the debiasing conceptor can utilize heterogeneous lists of biased words without loss in performance. Finally, our empirical experiments show that the debiasing conceptor diminishes racial and gender bias of word representations as measured using the Word Embedding Association Test (WEAT) of Caliskan et al. (2017).</abstract>
    <identifier type="citekey">karve-etal-2019-conceptor</identifier>
    <identifier type="doi">10.18653/v1/W19-3806</identifier>
    <location>
        <url>https://aclanthology.org/W19-3806</url>
    </location>
    <part>
        <date>2019-08</date>
        <extent unit="page">
            <start>40</start>
            <end>48</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Conceptor Debiasing of Word Representations Evaluated on WEAT
%A Karve, Saket
%A Ungar, Lyle
%A Sedoc, João
%Y Costa-jussà, Marta R.
%Y Hardmeier, Christian
%Y Radford, Will
%Y Webster, Kellie
%S Proceedings of the First Workshop on Gender Bias in Natural Language Processing
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F karve-etal-2019-conceptor
%X Bias in word representations, such as Word2Vec, has been widely reported and investigated, and efforts made to debias them. We apply the debiasing conceptor for post-processing both traditional and contextualized word embeddings. Our method can simultaneously remove racial and gender biases from word representations. Unlike standard debiasing methods, the debiasing conceptor can utilize heterogeneous lists of biased words without loss in performance. Finally, our empirical experiments show that the debiasing conceptor diminishes racial and gender bias of word representations as measured using the Word Embedding Association Test (WEAT) of Caliskan et al. (2017).
%R 10.18653/v1/W19-3806
%U https://aclanthology.org/W19-3806
%U https://doi.org/10.18653/v1/W19-3806
%P 40-48

Markdown (Informal)

[Conceptor Debiasing of Word Representations Evaluated on WEAT](https://aclanthology.org/W19-3806) (Karve et al., GeBNLP 2019)

• Conceptor Debiasing of Word Representations Evaluated on WEAT (Karve et al., GeBNLP 2019)

ACL

• Saket Karve, Lyle Ungar, and João Sedoc. 2019. Conceptor Debiasing of Word Representations Evaluated on WEAT. In Proceedings of the First Workshop on Gender Bias in Natural Language Processing, pages 40–48, Florence, Italy. Association for Computational Linguistics.