<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kaneko-bollegala-2019-gender">
    <titleInfo>
        <title>Gender-preserving Debiasing for Pre-trained Word Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Masahiro</namePart>
        <namePart type="family">Kaneko</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Danushka</namePart>
        <namePart type="family">Bollegala</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</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>Word embeddings learnt from massive text collections have demonstrated significant levels of discriminative biases such as gender, racial or ethnic biases, which in turn bias the down-stream NLP applications that use those word embeddings. Taking gender-bias as a working example, we propose a debiasing method that preserves non-discriminative gender-related information, while removing stereotypical discriminative gender biases from pre-trained word embeddings. Specifically, we consider four types of information: feminine, masculine, gender-neutral and stereotypical, which represent the relationship between gender vs. bias, and propose a debiasing method that (a) preserves the gender-related information in feminine and masculine words, (b) preserves the neutrality in gender-neutral words, and (c) removes the biases from stereotypical words. Experimental results on several previously proposed benchmark datasets show that our proposed method can debias pre-trained word embeddings better than existing SoTA methods proposed for debiasing word embeddings while preserving gender-related but non-discriminative information.</abstract>
    <identifier type="citekey">kaneko-bollegala-2019-gender</identifier>
    <identifier type="doi">10.18653/v1/P19-1160</identifier>
    <location>
        <url>https://aclanthology.org/P19-1160</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>1641</start>
            <end>1650</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Gender-preserving Debiasing for Pre-trained Word Embeddings
%A Kaneko, Masahiro
%A Bollegala, Danushka
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F kaneko-bollegala-2019-gender
%X Word embeddings learnt from massive text collections have demonstrated significant levels of discriminative biases such as gender, racial or ethnic biases, which in turn bias the down-stream NLP applications that use those word embeddings. Taking gender-bias as a working example, we propose a debiasing method that preserves non-discriminative gender-related information, while removing stereotypical discriminative gender biases from pre-trained word embeddings. Specifically, we consider four types of information: feminine, masculine, gender-neutral and stereotypical, which represent the relationship between gender vs. bias, and propose a debiasing method that (a) preserves the gender-related information in feminine and masculine words, (b) preserves the neutrality in gender-neutral words, and (c) removes the biases from stereotypical words. Experimental results on several previously proposed benchmark datasets show that our proposed method can debias pre-trained word embeddings better than existing SoTA methods proposed for debiasing word embeddings while preserving gender-related but non-discriminative information.
%R 10.18653/v1/P19-1160
%U https://aclanthology.org/P19-1160
%U https://doi.org/10.18653/v1/P19-1160
%P 1641-1650

Markdown (Informal)

[Gender-preserving Debiasing for Pre-trained Word Embeddings](https://aclanthology.org/P19-1160) (Kaneko & Bollegala, ACL 2019)

• Gender-preserving Debiasing for Pre-trained Word Embeddings (Kaneko & Bollegala, ACL 2019)

ACL

• Masahiro Kaneko and Danushka Bollegala. 2019. Gender-preserving Debiasing for Pre-trained Word Embeddings. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1641–1650, Florence, Italy. Association for Computational Linguistics.