<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-tsvetkov-2020-fortifying">
    <titleInfo>
        <title>Fortifying Toxic Speech Detectors Against Veiled Toxicity</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiaochuang</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yulia</namePart>
        <namePart type="family">Tsvetkov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Bonnie</namePart>
            <namePart type="family">Webber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</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>Modern toxic speech detectors are incompetent in recognizing disguised offensive language, such as adversarial attacks that deliberately avoid known toxic lexicons, or manifestations of implicit bias. Building a large annotated dataset for such veiled toxicity can be very expensive. In this work, we propose a framework aimed at fortifying existing toxic speech detectors without a large labeled corpus of veiled toxicity. Just a handful of probing examples are used to surface orders of magnitude more disguised offenses. We augment the toxic speech detector’s training data with these discovered offensive examples, thereby making it more robust to veiled toxicity while preserving its utility in detecting overt toxicity.</abstract>
    <identifier type="citekey">han-tsvetkov-2020-fortifying</identifier>
    <identifier type="doi">10.18653/v1/2020.emnlp-main.622</identifier>
    <location>
        <url>https://aclanthology.org/2020.emnlp-main.622</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>7732</start>
            <end>7739</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Fortifying Toxic Speech Detectors Against Veiled Toxicity
%A Han, Xiaochuang
%A Tsvetkov, Yulia
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F han-tsvetkov-2020-fortifying
%X Modern toxic speech detectors are incompetent in recognizing disguised offensive language, such as adversarial attacks that deliberately avoid known toxic lexicons, or manifestations of implicit bias. Building a large annotated dataset for such veiled toxicity can be very expensive. In this work, we propose a framework aimed at fortifying existing toxic speech detectors without a large labeled corpus of veiled toxicity. Just a handful of probing examples are used to surface orders of magnitude more disguised offenses. We augment the toxic speech detector’s training data with these discovered offensive examples, thereby making it more robust to veiled toxicity while preserving its utility in detecting overt toxicity.
%R 10.18653/v1/2020.emnlp-main.622
%U https://aclanthology.org/2020.emnlp-main.622
%U https://doi.org/10.18653/v1/2020.emnlp-main.622
%P 7732-7739

Markdown (Informal)

[Fortifying Toxic Speech Detectors Against Veiled Toxicity](https://aclanthology.org/2020.emnlp-main.622) (Han & Tsvetkov, EMNLP 2020)

• Fortifying Toxic Speech Detectors Against Veiled Toxicity (Han & Tsvetkov, EMNLP 2020)

ACL

• Xiaochuang Han and Yulia Tsvetkov. 2020. Fortifying Toxic Speech Detectors Against Veiled Toxicity. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7732–7739, Online. Association for Computational Linguistics.