@inproceedings{al-sabbagh-girju-2012-yadac,
title = "{YADAC}: Yet another Dialectal {A}rabic Corpus",
author = "Al-Sabbagh, Rania and
Girju, Roxana",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/663_Paper.pdf",
pages = "2882--2889",
abstract = "This paper presents the first phase of building YADAC ― a multi-genre Dialectal Arabic (DA) corpus ― that is compiled using Web data from microblogs (i.e. Twitter), blogs/forums and online knowledge market services in which both questions and answers are user-generated. In addition to introducing two new genres to the current efforts of building DA corpora (i.e. microblogs and question-answer pairs extracted from online knowledge market services), the paper highlights and tackles several new issues related to building DA corpora that have not been handled in previous studies: function-based Web harvesting and dialect identification, vowel-based spelling variation, linguistic hypercorrection and its effect on spelling variation, unsupervised Part-of-Speech (POS) tagging and base phrase chunking for DA. Although the algorithms for both POS tagging and base-phrase chunking are still under development, the results are promising.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-sabbagh-girju-2012-yadac">
<titleInfo>
<title>YADAC: Yet another Dialectal Arabic Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rania</namePart>
<namePart type="family">Al-Sabbagh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roxana</namePart>
<namePart type="family">Girju</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the first phase of building YADAC ― a multi-genre Dialectal Arabic (DA) corpus ― that is compiled using Web data from microblogs (i.e. Twitter), blogs/forums and online knowledge market services in which both questions and answers are user-generated. In addition to introducing two new genres to the current efforts of building DA corpora (i.e. microblogs and question-answer pairs extracted from online knowledge market services), the paper highlights and tackles several new issues related to building DA corpora that have not been handled in previous studies: function-based Web harvesting and dialect identification, vowel-based spelling variation, linguistic hypercorrection and its effect on spelling variation, unsupervised Part-of-Speech (POS) tagging and base phrase chunking for DA. Although the algorithms for both POS tagging and base-phrase chunking are still under development, the results are promising.</abstract>
<identifier type="citekey">al-sabbagh-girju-2012-yadac</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/663_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2882</start>
<end>2889</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T YADAC: Yet another Dialectal Arabic Corpus
%A Al-Sabbagh, Rania
%A Girju, Roxana
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F al-sabbagh-girju-2012-yadac
%X This paper presents the first phase of building YADAC ― a multi-genre Dialectal Arabic (DA) corpus ― that is compiled using Web data from microblogs (i.e. Twitter), blogs/forums and online knowledge market services in which both questions and answers are user-generated. In addition to introducing two new genres to the current efforts of building DA corpora (i.e. microblogs and question-answer pairs extracted from online knowledge market services), the paper highlights and tackles several new issues related to building DA corpora that have not been handled in previous studies: function-based Web harvesting and dialect identification, vowel-based spelling variation, linguistic hypercorrection and its effect on spelling variation, unsupervised Part-of-Speech (POS) tagging and base phrase chunking for DA. Although the algorithms for both POS tagging and base-phrase chunking are still under development, the results are promising.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/663_Paper.pdf
%P 2882-2889
Markdown (Informal)
[YADAC: Yet another Dialectal Arabic Corpus](http://www.lrec-conf.org/proceedings/lrec2012/pdf/663_Paper.pdf) (Al-Sabbagh & Girju, LREC 2012)
ACL
- Rania Al-Sabbagh and Roxana Girju. 2012. YADAC: Yet another Dialectal Arabic Corpus. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2882–2889, Istanbul, Turkey. European Language Resources Association (ELRA).