<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goldzycher-schneider-2022-hypothesis">
    <titleInfo>
        <title>Hypothesis Engineering for Zero-Shot Hate Speech Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Janis</namePart>
        <namePart type="family">Goldzycher</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gerold</namePart>
        <namePart type="family">Schneider</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Third Workshop on Threat, Aggression and Cyberbullying (TRAC 2022)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ritesh</namePart>
            <namePart type="family">Kumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Atul</namePart>
            <namePart type="given">Kr.</namePart>
            <namePart type="family">Ojha</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marcos</namePart>
            <namePart type="family">Zampieri</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shervin</namePart>
            <namePart type="family">Malmasi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Daniel</namePart>
            <namePart type="family">Kadar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Standard approaches to hate speech detection rely on sufficient available hate speech annotations. Extending previous work that repurposes natural language inference (NLI) models for zero-shot text classification, we propose a simple approach that combines multiple hypotheses to improve English NLI-based zero-shot hate speech detection. We first conduct an error analysis for vanilla NLI-based zero-shot hate speech detection and then develop four strategies based on this analysis. The strategies use multiple hypotheses to predict various aspects of an input text and combine these predictions into a final verdict. We find that the zero-shot baseline used for the initial error analysis already outperforms commercial systems and fine-tuned BERT-based hate speech detection models on HateCheck. The combination of the proposed strategies further increases the zero-shot accuracy of 79.4% on HateCheck by 7.9 percentage points (pp), and the accuracy of 69.6% on ETHOS by 10.0pp.</abstract>
    <identifier type="citekey">goldzycher-schneider-2022-hypothesis</identifier>
    <location>
        <url>https://aclanthology.org/2022.trac-1.10</url>
    </location>
    <part>
        <date>2022-10</date>
        <extent unit="page">
            <start>75</start>
            <end>90</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Hypothesis Engineering for Zero-Shot Hate Speech Detection
%A Goldzycher, Janis
%A Schneider, Gerold
%Y Kumar, Ritesh
%Y Ojha, Atul Kr.
%Y Zampieri, Marcos
%Y Malmasi, Shervin
%Y Kadar, Daniel
%S Proceedings of the Third Workshop on Threat, Aggression and Cyberbullying (TRAC 2022)
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F goldzycher-schneider-2022-hypothesis
%X Standard approaches to hate speech detection rely on sufficient available hate speech annotations. Extending previous work that repurposes natural language inference (NLI) models for zero-shot text classification, we propose a simple approach that combines multiple hypotheses to improve English NLI-based zero-shot hate speech detection. We first conduct an error analysis for vanilla NLI-based zero-shot hate speech detection and then develop four strategies based on this analysis. The strategies use multiple hypotheses to predict various aspects of an input text and combine these predictions into a final verdict. We find that the zero-shot baseline used for the initial error analysis already outperforms commercial systems and fine-tuned BERT-based hate speech detection models on HateCheck. The combination of the proposed strategies further increases the zero-shot accuracy of 79.4% on HateCheck by 7.9 percentage points (pp), and the accuracy of 69.6% on ETHOS by 10.0pp.
%U https://aclanthology.org/2022.trac-1.10
%P 75-90

Markdown (Informal)

[Hypothesis Engineering for Zero-Shot Hate Speech Detection](https://aclanthology.org/2022.trac-1.10) (Goldzycher & Schneider, TRAC 2022)

• Hypothesis Engineering for Zero-Shot Hate Speech Detection (Goldzycher & Schneider, TRAC 2022)

ACL

• Janis Goldzycher and Gerold Schneider. 2022. Hypothesis Engineering for Zero-Shot Hate Speech Detection. In Proceedings of the Third Workshop on Threat, Aggression and Cyberbullying (TRAC 2022), pages 75–90, Gyeongju, Republic of Korea. Association for Computational Linguistics.