@inproceedings{rottger-etal-2022-multilingual,
title = "Multilingual {H}ate{C}heck: Functional Tests for Multilingual Hate Speech Detection Models",
author = {R{\"o}ttger, Paul and
Seelawi, Haitham and
Nozza, Debora and
Talat, Zeerak and
Vidgen, Bertie},
editor = "Narang, Kanika and
Mostafazadeh Davani, Aida and
Mathias, Lambert and
Vidgen, Bertie and
Talat, Zeerak",
booktitle = "Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)",
month = jul,
year = "2022",
address = "Seattle, Washington (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.woah-1.15",
doi = "10.18653/v1/2022.woah-1.15",
pages = "154--169",
abstract = "Hate speech detection models are typically evaluated on held-out test sets. However, this risks painting an incomplete and potentially misleading picture of model performance because of increasingly well-documented systematic gaps and biases in hate speech datasets. To enable more targeted diagnostic insights, recent research has thus introduced functional tests for hate speech detection models. However, these tests currently only exist for English-language content, which means that they cannot support the development of more effective models in other languages spoken by billions across the world. To help address this issue, we introduce Multilingual HateCheck (MHC), a suite of functional tests for multilingual hate speech detection models. MHC covers 34 functionalities across ten languages, which is more languages than any other hate speech dataset. To illustrate MHC{'}s utility, we train and test a high-performing multilingual hate speech detection model, and reveal critical model weaknesses for monolingual and cross-lingual applications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rottger-etal-2022-multilingual">
<titleInfo>
<title>Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Röttger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haitham</namePart>
<namePart type="family">Seelawi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Talat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bertie</namePart>
<namePart type="family">Vidgen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kanika</namePart>
<namePart type="family">Narang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Mostafazadeh Davani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lambert</namePart>
<namePart type="family">Mathias</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">Zeerak</namePart>
<namePart type="family">Talat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Hate speech detection models are typically evaluated on held-out test sets. However, this risks painting an incomplete and potentially misleading picture of model performance because of increasingly well-documented systematic gaps and biases in hate speech datasets. To enable more targeted diagnostic insights, recent research has thus introduced functional tests for hate speech detection models. However, these tests currently only exist for English-language content, which means that they cannot support the development of more effective models in other languages spoken by billions across the world. To help address this issue, we introduce Multilingual HateCheck (MHC), a suite of functional tests for multilingual hate speech detection models. MHC covers 34 functionalities across ten languages, which is more languages than any other hate speech dataset. To illustrate MHC’s utility, we train and test a high-performing multilingual hate speech detection model, and reveal critical model weaknesses for monolingual and cross-lingual applications.</abstract>
<identifier type="citekey">rottger-etal-2022-multilingual</identifier>
<identifier type="doi">10.18653/v1/2022.woah-1.15</identifier>
<location>
<url>https://aclanthology.org/2022.woah-1.15</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>154</start>
<end>169</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models
%A Röttger, Paul
%A Seelawi, Haitham
%A Nozza, Debora
%A Talat, Zeerak
%A Vidgen, Bertie
%Y Narang, Kanika
%Y Mostafazadeh Davani, Aida
%Y Mathias, Lambert
%Y Vidgen, Bertie
%Y Talat, Zeerak
%S Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington (Hybrid)
%F rottger-etal-2022-multilingual
%X Hate speech detection models are typically evaluated on held-out test sets. However, this risks painting an incomplete and potentially misleading picture of model performance because of increasingly well-documented systematic gaps and biases in hate speech datasets. To enable more targeted diagnostic insights, recent research has thus introduced functional tests for hate speech detection models. However, these tests currently only exist for English-language content, which means that they cannot support the development of more effective models in other languages spoken by billions across the world. To help address this issue, we introduce Multilingual HateCheck (MHC), a suite of functional tests for multilingual hate speech detection models. MHC covers 34 functionalities across ten languages, which is more languages than any other hate speech dataset. To illustrate MHC’s utility, we train and test a high-performing multilingual hate speech detection model, and reveal critical model weaknesses for monolingual and cross-lingual applications.
%R 10.18653/v1/2022.woah-1.15
%U https://aclanthology.org/2022.woah-1.15
%U https://doi.org/10.18653/v1/2022.woah-1.15
%P 154-169
Markdown (Informal)
[Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models](https://aclanthology.org/2022.woah-1.15) (Röttger et al., WOAH 2022)
ACL