<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moslemi-zouaq-2024-tagdebias">
    <titleInfo>
        <title>TagDebias: Entity and Concept Tagging for Social Bias Mitigation in Pretrained Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mehrnaz</namePart>
        <namePart type="family">Moslemi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Amal</namePart>
        <namePart type="family">Zouaq</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kevin</namePart>
            <namePart type="family">Duh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Helena</namePart>
            <namePart type="family">Gomez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Bethard</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mexico City, Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Pre-trained language models (PLMs) play a crucial role in various applications, including sensitive domains such as the hiring process. However, extensive research has unveiled that these models tend to replicate social biases present in their pre-training data, raising ethical concerns. In this study, we propose the TagDebias method, which proposes debiasing a dataset using type tags. It then proceeds to fine-tune PLMs on this debiased dataset. Experiments show that our proposed TagDebias model, when applied to a ranking task, exhibits significant improvements in bias scores.</abstract>
    <identifier type="citekey">moslemi-zouaq-2024-tagdebias</identifier>
    <identifier type="doi">10.18653/v1/2024.findings-naacl.101</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-naacl.101</url>
    </location>
    <part>
        <date>2024-06</date>
        <extent unit="page">
            <start>1553</start>
            <end>1567</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TagDebias: Entity and Concept Tagging for Social Bias Mitigation in Pretrained Language Models
%A Moslemi, Mehrnaz
%A Zouaq, Amal
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F moslemi-zouaq-2024-tagdebias
%X Pre-trained language models (PLMs) play a crucial role in various applications, including sensitive domains such as the hiring process. However, extensive research has unveiled that these models tend to replicate social biases present in their pre-training data, raising ethical concerns. In this study, we propose the TagDebias method, which proposes debiasing a dataset using type tags. It then proceeds to fine-tune PLMs on this debiased dataset. Experiments show that our proposed TagDebias model, when applied to a ranking task, exhibits significant improvements in bias scores.
%R 10.18653/v1/2024.findings-naacl.101
%U https://aclanthology.org/2024.findings-naacl.101
%U https://doi.org/10.18653/v1/2024.findings-naacl.101
%P 1553-1567

Markdown (Informal)

[TagDebias: Entity and Concept Tagging for Social Bias Mitigation in Pretrained Language Models](https://aclanthology.org/2024.findings-naacl.101) (Moslemi & Zouaq, Findings 2024)

• TagDebias: Entity and Concept Tagging for Social Bias Mitigation in Pretrained Language Models (Moslemi & Zouaq, Findings 2024)

ACL

• Mehrnaz Moslemi and Amal Zouaq. 2024. TagDebias: Entity and Concept Tagging for Social Bias Mitigation in Pretrained Language Models. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 1553–1567, Mexico City, Mexico. Association for Computational Linguistics.