@inproceedings{salama-etal-2014-youdacc,
title = "{Y}ou{DACC}: the {Y}outube Dialectal {A}rabic Comment Corpus",
author = "Salama, Ahmed and
Bouamor, Houda and
Mohit, Behrang and
Oflazer, Kemal",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/558_Paper.pdf",
pages = "1246--1251",
abstract = "This paper presents YOUDACC, an automatically annotated large-scale multi-dialectal Arabic corpus collected from user comments on Youtube videos. Our corpus covers different groups of dialects: Egyptian (EG), Gulf (GU), Iraqi (IQ), Maghrebi (MG) and Levantine (LV). We perform an empirical analysis on the crawled corpus and demonstrate that our location-based proposed method is effective for the task of dialect labeling.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salama-etal-2014-youdacc">
<titleInfo>
<title>YouDACC: the Youtube Dialectal Arabic Comment Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Salama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Behrang</namePart>
<namePart type="family">Mohit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kemal</namePart>
<namePart type="family">Oflazer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</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">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 (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents YOUDACC, an automatically annotated large-scale multi-dialectal Arabic corpus collected from user comments on Youtube videos. Our corpus covers different groups of dialects: Egyptian (EG), Gulf (GU), Iraqi (IQ), Maghrebi (MG) and Levantine (LV). We perform an empirical analysis on the crawled corpus and demonstrate that our location-based proposed method is effective for the task of dialect labeling.</abstract>
<identifier type="citekey">salama-etal-2014-youdacc</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/558_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1246</start>
<end>1251</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T YouDACC: the Youtube Dialectal Arabic Comment Corpus
%A Salama, Ahmed
%A Bouamor, Houda
%A Mohit, Behrang
%A Oflazer, Kemal
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F salama-etal-2014-youdacc
%X This paper presents YOUDACC, an automatically annotated large-scale multi-dialectal Arabic corpus collected from user comments on Youtube videos. Our corpus covers different groups of dialects: Egyptian (EG), Gulf (GU), Iraqi (IQ), Maghrebi (MG) and Levantine (LV). We perform an empirical analysis on the crawled corpus and demonstrate that our location-based proposed method is effective for the task of dialect labeling.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/558_Paper.pdf
%P 1246-1251
Markdown (Informal)
[YouDACC: the Youtube Dialectal Arabic Comment Corpus](http://www.lrec-conf.org/proceedings/lrec2014/pdf/558_Paper.pdf) (Salama et al., LREC 2014)
ACL
- Ahmed Salama, Houda Bouamor, Behrang Mohit, and Kemal Oflazer. 2014. YouDACC: the Youtube Dialectal Arabic Comment Corpus. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1246–1251, Reykjavik, Iceland. European Language Resources Association (ELRA).