<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kaneko-etal-2022-gender-bias">
    <titleInfo>
        <title>Gender Bias in Meta-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>
    <name type="personal">
        <namePart type="given">Naoaki</namePart>
        <namePart type="family">Okazaki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Different methods have been proposed to develop meta-embeddings from a given set of source embeddings. However, the source embeddings can contain unfair gender-related biases, and how these influence the meta-embeddings has not been studied yet. We study the gender bias in meta-embeddings created under three different settings:(1) meta-embedding multiple sources without performing any debiasing (Multi-Source No-Debiasing),(2) meta-embedding multiple sources debiased by a single method (Multi-Source Single-Debiasing), and(3) meta-embedding a single source debiased by different methods (Single-Source Multi-Debiasing).Our experimental results show that meta-embedding amplifies the gender biases compared to input source embeddings.We find that debiasing not only the sources but also their meta-embedding is needed to mitigate those biases. Moreover, we propose a novel debiasing method based on meta-embedding learning where we use multiple debiasing methods on a single source embedding and then create a single unbiased meta-embedding.</abstract>
    <identifier type="citekey">kaneko-etal-2022-gender-bias</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.227</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.227</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>3118</start>
            <end>3133</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Gender Bias in Meta-Embeddings
%A Kaneko, Masahiro
%A Bollegala, Danushka
%A Okazaki, Naoaki
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F kaneko-etal-2022-gender-bias
%X Different methods have been proposed to develop meta-embeddings from a given set of source embeddings. However, the source embeddings can contain unfair gender-related biases, and how these influence the meta-embeddings has not been studied yet. We study the gender bias in meta-embeddings created under three different settings:(1) meta-embedding multiple sources without performing any debiasing (Multi-Source No-Debiasing),(2) meta-embedding multiple sources debiased by a single method (Multi-Source Single-Debiasing), and(3) meta-embedding a single source debiased by different methods (Single-Source Multi-Debiasing).Our experimental results show that meta-embedding amplifies the gender biases compared to input source embeddings.We find that debiasing not only the sources but also their meta-embedding is needed to mitigate those biases. Moreover, we propose a novel debiasing method based on meta-embedding learning where we use multiple debiasing methods on a single source embedding and then create a single unbiased meta-embedding.
%R 10.18653/v1/2022.findings-emnlp.227
%U https://aclanthology.org/2022.findings-emnlp.227
%U https://doi.org/10.18653/v1/2022.findings-emnlp.227
%P 3118-3133

Markdown (Informal)

[Gender Bias in Meta-Embeddings](https://aclanthology.org/2022.findings-emnlp.227) (Kaneko et al., Findings 2022)

• Gender Bias in Meta-Embeddings (Kaneko et al., Findings 2022)

ACL

• Masahiro Kaneko, Danushka Bollegala, and Naoaki Okazaki. 2022. Gender Bias in Meta-Embeddings. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3118–3133, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.