<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2022-balancing">
    <titleInfo>
        <title>Balancing out Bias: Achieving Fairness Through Balanced Training</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xudong</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Timothy</namePart>
        <namePart type="family">Baldwin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Trevor</namePart>
        <namePart type="family">Cohn</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>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</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>Group bias in natural language processing tasks manifests as disparities in system error rates across texts authorized by different demographic groups, typically disadvantaging minority groups. Dataset balancing has been shown to be effective at mitigating bias, however existing approaches do not directly account for correlations between author demographics and linguistic variables, limiting their effectiveness. To achieve Equal Opportunity fairness, such as equal job opportunity without regard to demographics, this paper introduces a simple, but highly effective, objective for countering bias using balanced training. We extend the method in the form of a gated model, which incorporates protected attributes as input, and show that it is effective at reducing bias in predictions through demographic input perturbation, outperforming all other bias mitigation techniques when combined with balanced training.</abstract>
    <identifier type="citekey">han-etal-2022-balancing</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.779</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.779</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>11335</start>
            <end>11350</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Balancing out Bias: Achieving Fairness Through Balanced Training
%A Han, Xudong
%A Baldwin, Timothy
%A Cohn, Trevor
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F han-etal-2022-balancing
%X Group bias in natural language processing tasks manifests as disparities in system error rates across texts authorized by different demographic groups, typically disadvantaging minority groups. Dataset balancing has been shown to be effective at mitigating bias, however existing approaches do not directly account for correlations between author demographics and linguistic variables, limiting their effectiveness. To achieve Equal Opportunity fairness, such as equal job opportunity without regard to demographics, this paper introduces a simple, but highly effective, objective for countering bias using balanced training. We extend the method in the form of a gated model, which incorporates protected attributes as input, and show that it is effective at reducing bias in predictions through demographic input perturbation, outperforming all other bias mitigation techniques when combined with balanced training.
%R 10.18653/v1/2022.emnlp-main.779
%U https://aclanthology.org/2022.emnlp-main.779
%U https://doi.org/10.18653/v1/2022.emnlp-main.779
%P 11335-11350

Markdown (Informal)

[Balancing out Bias: Achieving Fairness Through Balanced Training](https://aclanthology.org/2022.emnlp-main.779) (Han et al., EMNLP 2022)

• Balancing out Bias: Achieving Fairness Through Balanced Training (Han et al., EMNLP 2022)

ACL

• Xudong Han, Timothy Baldwin, and Trevor Cohn. 2022. Balancing out Bias: Achieving Fairness Through Balanced Training. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11335–11350, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.