<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hutchinson-etal-2020-social">
    <titleInfo>
        <title>Social Biases in NLP Models as Barriers for Persons with Disabilities</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ben</namePart>
        <namePart type="family">Hutchinson</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vinodkumar</namePart>
        <namePart type="family">Prabhakaran</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Emily</namePart>
        <namePart type="family">Denton</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kellie</namePart>
        <namePart type="family">Webster</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yu</namePart>
        <namePart type="family">Zhong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stephen</namePart>
        <namePart type="family">Denuyl</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Dan</namePart>
            <namePart type="family">Jurafsky</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Chai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Natalie</namePart>
            <namePart type="family">Schluter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joel</namePart>
            <namePart type="family">Tetreault</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Building equitable and inclusive NLP technologies demands consideration of whether and how social attitudes are represented in ML models. In particular, representations encoded in models often inadvertently perpetuate undesirable social biases from the data on which they are trained. In this paper, we present evidence of such undesirable biases towards mentions of disability in two different English language models: toxicity prediction and sentiment analysis. Next, we demonstrate that the neural embeddings that are the critical first step in most NLP pipelines similarly contain undesirable biases towards mentions of disability. We end by highlighting topical biases in the discourse about disability which may contribute to the observed model biases; for instance, gun violence, homelessness, and drug addiction are over-represented in texts discussing mental illness.</abstract>
    <identifier type="citekey">hutchinson-etal-2020-social</identifier>
    <identifier type="doi">10.18653/v1/2020.acl-main.487</identifier>
    <location>
        <url>https://aclanthology.org/2020.acl-main.487</url>
    </location>
    <part>
        <date>2020-07</date>
        <extent unit="page">
            <start>5491</start>
            <end>5501</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Social Biases in NLP Models as Barriers for Persons with Disabilities
%A Hutchinson, Ben
%A Prabhakaran, Vinodkumar
%A Denton, Emily
%A Webster, Kellie
%A Zhong, Yu
%A Denuyl, Stephen
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F hutchinson-etal-2020-social
%X Building equitable and inclusive NLP technologies demands consideration of whether and how social attitudes are represented in ML models. In particular, representations encoded in models often inadvertently perpetuate undesirable social biases from the data on which they are trained. In this paper, we present evidence of such undesirable biases towards mentions of disability in two different English language models: toxicity prediction and sentiment analysis. Next, we demonstrate that the neural embeddings that are the critical first step in most NLP pipelines similarly contain undesirable biases towards mentions of disability. We end by highlighting topical biases in the discourse about disability which may contribute to the observed model biases; for instance, gun violence, homelessness, and drug addiction are over-represented in texts discussing mental illness.
%R 10.18653/v1/2020.acl-main.487
%U https://aclanthology.org/2020.acl-main.487
%U https://doi.org/10.18653/v1/2020.acl-main.487
%P 5491-5501

Markdown (Informal)

[Social Biases in NLP Models as Barriers for Persons with Disabilities](https://aclanthology.org/2020.acl-main.487) (Hutchinson et al., ACL 2020)

• Social Biases in NLP Models as Barriers for Persons with Disabilities (Hutchinson et al., ACL 2020)

ACL

• Ben Hutchinson, Vinodkumar Prabhakaran, Emily Denton, Kellie Webster, Yu Zhong, and Stephen Denuyl. 2020. Social Biases in NLP Models as Barriers for Persons with Disabilities. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5491–5501, Online. Association for Computational Linguistics.