@inproceedings{glavas-etal-2020-xhate,
title = "{XH}ate-999: Analyzing and Detecting Abusive Language Across Domains and Languages",
author = "Glava{\v{s}}, Goran and
Karan, Mladen and
Vuli{\'c}, Ivan",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.559",
doi = "10.18653/v1/2020.coling-main.559",
pages = "6350--6365",
abstract = "We present XHate-999, a multi-domain and multilingual evaluation data set for abusive language detection. By aligning test instances across six typologically diverse languages, XHate-999 for the first time allows for disentanglement of the domain transfer and language transfer effects in abusive language detection. We conduct a series of domain- and language-transfer experiments with state-of-the-art monolingual and multilingual transformer models, setting strong baseline results and profiling XHate-999 as a comprehensive evaluation resource for abusive language detection. Finally, we show that domain- and language-adaption, via intermediate masked language modeling on abusive corpora in the target language, can lead to substantially improved abusive language detection in the target language in the zero-shot transfer setups.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="glavas-etal-2020-xhate">
<titleInfo>
<title>XHate-999: Analyzing and Detecting Abusive Language Across Domains and Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Glavaš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mladen</namePart>
<namePart type="family">Karan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present XHate-999, a multi-domain and multilingual evaluation data set for abusive language detection. By aligning test instances across six typologically diverse languages, XHate-999 for the first time allows for disentanglement of the domain transfer and language transfer effects in abusive language detection. We conduct a series of domain- and language-transfer experiments with state-of-the-art monolingual and multilingual transformer models, setting strong baseline results and profiling XHate-999 as a comprehensive evaluation resource for abusive language detection. Finally, we show that domain- and language-adaption, via intermediate masked language modeling on abusive corpora in the target language, can lead to substantially improved abusive language detection in the target language in the zero-shot transfer setups.</abstract>
<identifier type="citekey">glavas-etal-2020-xhate</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.559</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.559</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>6350</start>
<end>6365</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T XHate-999: Analyzing and Detecting Abusive Language Across Domains and Languages
%A Glavaš, Goran
%A Karan, Mladen
%A Vulić, Ivan
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F glavas-etal-2020-xhate
%X We present XHate-999, a multi-domain and multilingual evaluation data set for abusive language detection. By aligning test instances across six typologically diverse languages, XHate-999 for the first time allows for disentanglement of the domain transfer and language transfer effects in abusive language detection. We conduct a series of domain- and language-transfer experiments with state-of-the-art monolingual and multilingual transformer models, setting strong baseline results and profiling XHate-999 as a comprehensive evaluation resource for abusive language detection. Finally, we show that domain- and language-adaption, via intermediate masked language modeling on abusive corpora in the target language, can lead to substantially improved abusive language detection in the target language in the zero-shot transfer setups.
%R 10.18653/v1/2020.coling-main.559
%U https://aclanthology.org/2020.coling-main.559
%U https://doi.org/10.18653/v1/2020.coling-main.559
%P 6350-6365
Markdown (Informal)
[XHate-999: Analyzing and Detecting Abusive Language Across Domains and Languages](https://aclanthology.org/2020.coling-main.559) (Glavaš et al., COLING 2020)
ACL