<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ozler-etal-2020-fine">
    <titleInfo>
        <title>Fine-tuning for multi-domain and multi-label uncivil language detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kadir</namePart>
        <namePart type="given">Bulut</namePart>
        <namePart type="family">Ozler</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kate</namePart>
        <namePart type="family">Kenski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Steve</namePart>
        <namePart type="family">Rains</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yotam</namePart>
        <namePart type="family">Shmargad</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kevin</namePart>
        <namePart type="family">Coe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Steven</namePart>
        <namePart type="family">Bethard</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 Fourth Workshop on Online Abuse and Harms</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Seyi</namePart>
            <namePart type="family">Akiwowo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Bertie</namePart>
            <namePart type="family">Vidgen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vinodkumar</namePart>
            <namePart type="family">Prabhakaran</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zeerak</namePart>
            <namePart type="family">Waseem</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>Incivility is a problem on social media, and it comes in many forms (name-calling, vulgarity, threats, etc.) and domains (microblog posts, online news comments, Wikipedia edits, etc.). Training machine learning models to detect such incivility must handle the multi-label and multi-domain nature of the problem. We present a BERT-based model for incivility detection and propose several approaches for training it for multi-label and multi-domain datasets. We find that individual binary classifiers outperform a joint multi-label classifier, and that simply combining multiple domains of training data outperforms other recently-proposed fine tuning strategies. We also establish new state-of-the-art performance on several incivility detection datasets.</abstract>
    <identifier type="citekey">ozler-etal-2020-fine</identifier>
    <identifier type="doi">10.18653/v1/2020.alw-1.4</identifier>
    <location>
        <url>https://aclanthology.org/2020.alw-1.4/</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>28</start>
            <end>33</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Fine-tuning for multi-domain and multi-label uncivil language detection
%A Ozler, Kadir Bulut
%A Kenski, Kate
%A Rains, Steve
%A Shmargad, Yotam
%A Coe, Kevin
%A Bethard, Steven
%Y Akiwowo, Seyi
%Y Vidgen, Bertie
%Y Prabhakaran, Vinodkumar
%Y Waseem, Zeerak
%S Proceedings of the Fourth Workshop on Online Abuse and Harms
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F ozler-etal-2020-fine
%X Incivility is a problem on social media, and it comes in many forms (name-calling, vulgarity, threats, etc.) and domains (microblog posts, online news comments, Wikipedia edits, etc.). Training machine learning models to detect such incivility must handle the multi-label and multi-domain nature of the problem. We present a BERT-based model for incivility detection and propose several approaches for training it for multi-label and multi-domain datasets. We find that individual binary classifiers outperform a joint multi-label classifier, and that simply combining multiple domains of training data outperforms other recently-proposed fine tuning strategies. We also establish new state-of-the-art performance on several incivility detection datasets.
%R 10.18653/v1/2020.alw-1.4
%U https://aclanthology.org/2020.alw-1.4/
%U https://doi.org/10.18653/v1/2020.alw-1.4
%P 28-33

Markdown (Informal)

[Fine-tuning for multi-domain and multi-label uncivil language detection](https://aclanthology.org/2020.alw-1.4/) (Ozler et al., ALW 2020)

• Fine-tuning for multi-domain and multi-label uncivil language detection (Ozler et al., ALW 2020)

ACL

• Kadir Bulut Ozler, Kate Kenski, Steve Rains, Yotam Shmargad, Kevin Coe, and Steven Bethard. 2020. Fine-tuning for multi-domain and multi-label uncivil language detection. In Proceedings of the Fourth Workshop on Online Abuse and Harms, pages 28–33, Online. Association for Computational Linguistics.