@inproceedings{tian-kubler-2020-offensive,
title = "Offensive Language Detection Using Brown Clustering",
author = {Tian, Zuoyu and
K{\"u}bler, Sandra},
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.625",
pages = "5079--5087",
abstract = "In this study, we investigate the use of Brown clustering for offensive language detection. Brown clustering has been shown to be of little use when the task involves distinguishing word polarity in sentiment analysis tasks. In contrast to previous work, we train Brown clusters separately on positive and negative sentiment data, but then combine the information into a single complex feature per word. This way of representing words results in stable improvements in offensive language detection, when used as the only features or in combination with words or character n-grams. Brown clusters add important information, even when combined with words or character n-grams or with standard word embeddings in a convolutional neural network. However, we also found different trends between the two offensive language data sets we used.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tian-kubler-2020-offensive">
<titleInfo>
<title>Offensive Language Detection Using Brown Clustering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zuoyu</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Kübler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In this study, we investigate the use of Brown clustering for offensive language detection. Brown clustering has been shown to be of little use when the task involves distinguishing word polarity in sentiment analysis tasks. In contrast to previous work, we train Brown clusters separately on positive and negative sentiment data, but then combine the information into a single complex feature per word. This way of representing words results in stable improvements in offensive language detection, when used as the only features or in combination with words or character n-grams. Brown clusters add important information, even when combined with words or character n-grams or with standard word embeddings in a convolutional neural network. However, we also found different trends between the two offensive language data sets we used.</abstract>
<identifier type="citekey">tian-kubler-2020-offensive</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.625</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>5079</start>
<end>5087</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Offensive Language Detection Using Brown Clustering
%A Tian, Zuoyu
%A Kübler, Sandra
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F tian-kubler-2020-offensive
%X In this study, we investigate the use of Brown clustering for offensive language detection. Brown clustering has been shown to be of little use when the task involves distinguishing word polarity in sentiment analysis tasks. In contrast to previous work, we train Brown clusters separately on positive and negative sentiment data, but then combine the information into a single complex feature per word. This way of representing words results in stable improvements in offensive language detection, when used as the only features or in combination with words or character n-grams. Brown clusters add important information, even when combined with words or character n-grams or with standard word embeddings in a convolutional neural network. However, we also found different trends between the two offensive language data sets we used.
%U https://aclanthology.org/2020.lrec-1.625
%P 5079-5087
Markdown (Informal)
[Offensive Language Detection Using Brown Clustering](https://aclanthology.org/2020.lrec-1.625) (Tian & Kübler, LREC 2020)
ACL