<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-avci-2019-incorporating">
    <titleInfo>
        <title>Incorporating Priors with Feature Attribution on Text Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Frederick</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Besim</namePart>
        <namePart type="family">Avci</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>Feature attribution methods, proposed recently, help users interpret the predictions of complex models. Our approach integrates feature attributions into the objective function to allow machine learning practitioners to incorporate priors in model building. To demonstrate the effectiveness our technique, we apply it to two tasks: (1) mitigating unintended bias in text classifiers by neutralizing identity terms; (2) improving classifier performance in scarce data setting by forcing model to focus on toxic terms. Our approach adds an L2 distance loss between feature attributions and task-specific prior values to the objective. Our experiments show that i) a classifier trained with our technique reduces undesired model biases without a tradeoff on the original task; ii) incorporating prior helps model performance in scarce data settings.</abstract>
    <identifier type="citekey">liu-avci-2019-incorporating</identifier>
    <identifier type="doi">10.18653/v1/P19-1631</identifier>
    <location>
        <url>https://aclanthology.org/P19-1631</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>6274</start>
            <end>6283</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Incorporating Priors with Feature Attribution on Text Classification
%A Liu, Frederick
%A Avci, Besim
%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 liu-avci-2019-incorporating
%X Feature attribution methods, proposed recently, help users interpret the predictions of complex models. Our approach integrates feature attributions into the objective function to allow machine learning practitioners to incorporate priors in model building. To demonstrate the effectiveness our technique, we apply it to two tasks: (1) mitigating unintended bias in text classifiers by neutralizing identity terms; (2) improving classifier performance in scarce data setting by forcing model to focus on toxic terms. Our approach adds an L2 distance loss between feature attributions and task-specific prior values to the objective. Our experiments show that i) a classifier trained with our technique reduces undesired model biases without a tradeoff on the original task; ii) incorporating prior helps model performance in scarce data settings.
%R 10.18653/v1/P19-1631
%U https://aclanthology.org/P19-1631
%U https://doi.org/10.18653/v1/P19-1631
%P 6274-6283

Markdown (Informal)

[Incorporating Priors with Feature Attribution on Text Classification](https://aclanthology.org/P19-1631) (Liu & Avci, ACL 2019)

• Incorporating Priors with Feature Attribution on Text Classification (Liu & Avci, ACL 2019)

ACL

• Frederick Liu and Besim Avci. 2019. Incorporating Priors with Feature Attribution on Text Classification. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6274–6283, Florence, Italy. Association for Computational Linguistics.