@inproceedings{sjobergh-araki-2008-multi,
title = "A Multi-Lingual Dictionary of Dirty Words",
author = {Sj{\"o}bergh, Jonas and
Araki, Kenji},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/133_paper.pdf",
abstract = "We present a multi-lingual dictionary of dirty words. We have collected about 3,200 dirty words in several languages and built a database of these. The language with the most words in the database is English, though there are several hundred dirty words in for instance Japanese too. Words are classified into their general meaning, such as what part of the human anatomy they refer to. Words can also be assigned a nuance label to indicate if it is a cute word used when speaking to children, a very rude word, a clinical word etc. The database is available online and will hopefully be enlarged over time. It has already been used in research on for instance automatic joke generation and emotion detection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sjobergh-araki-2008-multi">
<titleInfo>
<title>A Multi-Lingual Dictionary of Dirty Words</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Sjöbergh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenji</namePart>
<namePart type="family">Araki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">Khalid</namePart>
<namePart type="family">Choukri</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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a multi-lingual dictionary of dirty words. We have collected about 3,200 dirty words in several languages and built a database of these. The language with the most words in the database is English, though there are several hundred dirty words in for instance Japanese too. Words are classified into their general meaning, such as what part of the human anatomy they refer to. Words can also be assigned a nuance label to indicate if it is a cute word used when speaking to children, a very rude word, a clinical word etc. The database is available online and will hopefully be enlarged over time. It has already been used in research on for instance automatic joke generation and emotion detection.</abstract>
<identifier type="citekey">sjobergh-araki-2008-multi</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/133_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Multi-Lingual Dictionary of Dirty Words
%A Sjöbergh, Jonas
%A Araki, Kenji
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F sjobergh-araki-2008-multi
%X We present a multi-lingual dictionary of dirty words. We have collected about 3,200 dirty words in several languages and built a database of these. The language with the most words in the database is English, though there are several hundred dirty words in for instance Japanese too. Words are classified into their general meaning, such as what part of the human anatomy they refer to. Words can also be assigned a nuance label to indicate if it is a cute word used when speaking to children, a very rude word, a clinical word etc. The database is available online and will hopefully be enlarged over time. It has already been used in research on for instance automatic joke generation and emotion detection.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/133_paper.pdf
Markdown (Informal)
[A Multi-Lingual Dictionary of Dirty Words](http://www.lrec-conf.org/proceedings/lrec2008/pdf/133_paper.pdf) (Sjöbergh & Araki, LREC 2008)
ACL
- Jonas Sjöbergh and Kenji Araki. 2008. A Multi-Lingual Dictionary of Dirty Words. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).