@inproceedings{pitenis-etal-2020-offensive,
title = "Offensive Language Identification in {G}reek",
author = "Pitenis, Zesis and
Zampieri, Marcos and
Ranasinghe, Tharindu",
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-1.629",
pages = "5113--5119",
abstract = "As offensive language has become a rising issue for online communities and social media platforms, researchers have been investigating ways of coping with abusive content and developing systems to detect its different types: cyberbullying, hate speech, aggression, etc. With a few notable exceptions, most research on this topic so far has dealt with English. This is mostly due to the availability of language resources for English. To address this shortcoming, this paper presents the first Greek annotated dataset for offensive language identification: the Offensive Greek Tweet Dataset (OGTD). OGTD is a manually annotated dataset containing 4,779 posts from Twitter annotated as offensive and not offensive. Along with a detailed description of the dataset, we evaluate several computational models trained and tested on this data.",
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="pitenis-etal-2020-offensive">
<titleInfo>
<title>Offensive Language Identification in Greek</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zesis</namePart>
<namePart type="family">Pitenis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</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>As offensive language has become a rising issue for online communities and social media platforms, researchers have been investigating ways of coping with abusive content and developing systems to detect its different types: cyberbullying, hate speech, aggression, etc. With a few notable exceptions, most research on this topic so far has dealt with English. This is mostly due to the availability of language resources for English. To address this shortcoming, this paper presents the first Greek annotated dataset for offensive language identification: the Offensive Greek Tweet Dataset (OGTD). OGTD is a manually annotated dataset containing 4,779 posts from Twitter annotated as offensive and not offensive. Along with a detailed description of the dataset, we evaluate several computational models trained and tested on this data.</abstract>
<identifier type="citekey">pitenis-etal-2020-offensive</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.629</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>5113</start>
<end>5119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Offensive Language Identification in Greek
%A Pitenis, Zesis
%A Zampieri, Marcos
%A Ranasinghe, Tharindu
%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 pitenis-etal-2020-offensive
%X As offensive language has become a rising issue for online communities and social media platforms, researchers have been investigating ways of coping with abusive content and developing systems to detect its different types: cyberbullying, hate speech, aggression, etc. With a few notable exceptions, most research on this topic so far has dealt with English. This is mostly due to the availability of language resources for English. To address this shortcoming, this paper presents the first Greek annotated dataset for offensive language identification: the Offensive Greek Tweet Dataset (OGTD). OGTD is a manually annotated dataset containing 4,779 posts from Twitter annotated as offensive and not offensive. Along with a detailed description of the dataset, we evaluate several computational models trained and tested on this data.
%U https://aclanthology.org/2020.lrec-1.629
%P 5113-5119
Markdown (Informal)
[Offensive Language Identification in Greek](https://aclanthology.org/2020.lrec-1.629) (Pitenis et al., LREC 2020)
ACL
- Zesis Pitenis, Marcos Zampieri, and Tharindu Ranasinghe. 2020. Offensive Language Identification in Greek. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 5113–5119, Marseille, France. European Language Resources Association.