<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wullach-etal-2021-fight-fire">
    <titleInfo>
        <title>Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate Speech</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tomer</namePart>
        <namePart type="family">Wullach</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Amir</namePart>
        <namePart type="family">Adler</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Einat</namePart>
        <namePart type="family">Minkov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Automatic hate speech detection is hampered by the scarcity of labeled datasetd, leading to poor generalization. We employ pretrained language models (LMs) to alleviate this data bottleneck. We utilize the GPT LM for generating large amounts of synthetic hate speech sequences from available labeled examples, and leverage the generated data in fine-tuning large pretrained LMs on hate detection. An empirical study using the models of BERT, RoBERTa and ALBERT, shows that this approach improves generalization significantly and consistently within and across data distributions. In fact, we find that generating relevant labeled hate speech sequences is preferable to using out-of-domain, and sometimes also within-domain, human-labeled examples.</abstract>
    <identifier type="citekey">wullach-etal-2021-fight-fire</identifier>
    <identifier type="doi">10.18653/v1/2021.findings-emnlp.402</identifier>
    <location>
        <url>https://aclanthology.org/2021.findings-emnlp.402</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>4699</start>
            <end>4705</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate Speech
%A Wullach, Tomer
%A Adler, Amir
%A Minkov, Einat
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F wullach-etal-2021-fight-fire
%X Automatic hate speech detection is hampered by the scarcity of labeled datasetd, leading to poor generalization. We employ pretrained language models (LMs) to alleviate this data bottleneck. We utilize the GPT LM for generating large amounts of synthetic hate speech sequences from available labeled examples, and leverage the generated data in fine-tuning large pretrained LMs on hate detection. An empirical study using the models of BERT, RoBERTa and ALBERT, shows that this approach improves generalization significantly and consistently within and across data distributions. In fact, we find that generating relevant labeled hate speech sequences is preferable to using out-of-domain, and sometimes also within-domain, human-labeled examples.
%R 10.18653/v1/2021.findings-emnlp.402
%U https://aclanthology.org/2021.findings-emnlp.402
%U https://doi.org/10.18653/v1/2021.findings-emnlp.402
%P 4699-4705

Markdown (Informal)

[Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate Speech](https://aclanthology.org/2021.findings-emnlp.402) (Wullach et al., Findings 2021)

• Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate Speech (Wullach et al., Findings 2021)

ACL

• Tomer Wullach, Amir Adler, and Einat Minkov. 2021. Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate Speech. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4699–4705, Punta Cana, Dominican Republic. Association for Computational Linguistics.