@inproceedings{elfardy-diab-2012-simplified,
title = "Simplified guidelines for the creation of Large Scale Dialectal {A}rabic Annotations",
author = "Elfardy, Heba and
Diab, Mona",
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/815_Paper.pdf",
pages = "371--378",
abstract = "The Arabic language is a collection of dialectal variants along with the standard form, Modern Standard Arabic (MSA). MSA is used in official Settings while the dialectal variants (DA) correspond to the native tongue of the Arabic speakers. Arabic speakers typically code switch between DA and MSA, which is reflected extensively in written online social media. Automatic processing such Arabic genre is very difficult for automated NLP tools since the linguistic difference between MSA and DA is quite profound. However, no annotated resources exist for marking the regions of such switches in the utterance. In this paper, we present a simplified Set of guidelines for detecting code switching in Arabic on the word/token level. We use these guidelines in annotating a corpus that is rich in DA with frequent code switching to MSA. We present both a quantitative and qualitative analysis of the annotations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elfardy-diab-2012-simplified">
<titleInfo>
<title>Simplified guidelines for the creation of Large Scale Dialectal Arabic Annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heba</namePart>
<namePart type="family">Elfardy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</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>The Arabic language is a collection of dialectal variants along with the standard form, Modern Standard Arabic (MSA). MSA is used in official Settings while the dialectal variants (DA) correspond to the native tongue of the Arabic speakers. Arabic speakers typically code switch between DA and MSA, which is reflected extensively in written online social media. Automatic processing such Arabic genre is very difficult for automated NLP tools since the linguistic difference between MSA and DA is quite profound. However, no annotated resources exist for marking the regions of such switches in the utterance. In this paper, we present a simplified Set of guidelines for detecting code switching in Arabic on the word/token level. We use these guidelines in annotating a corpus that is rich in DA with frequent code switching to MSA. We present both a quantitative and qualitative analysis of the annotations.</abstract>
<identifier type="citekey">elfardy-diab-2012-simplified</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/815_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>371</start>
<end>378</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simplified guidelines for the creation of Large Scale Dialectal Arabic Annotations
%A Elfardy, Heba
%A Diab, Mona
%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 elfardy-diab-2012-simplified
%X The Arabic language is a collection of dialectal variants along with the standard form, Modern Standard Arabic (MSA). MSA is used in official Settings while the dialectal variants (DA) correspond to the native tongue of the Arabic speakers. Arabic speakers typically code switch between DA and MSA, which is reflected extensively in written online social media. Automatic processing such Arabic genre is very difficult for automated NLP tools since the linguistic difference between MSA and DA is quite profound. However, no annotated resources exist for marking the regions of such switches in the utterance. In this paper, we present a simplified Set of guidelines for detecting code switching in Arabic on the word/token level. We use these guidelines in annotating a corpus that is rich in DA with frequent code switching to MSA. We present both a quantitative and qualitative analysis of the annotations.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/815_Paper.pdf
%P 371-378
Markdown (Informal)
[Simplified guidelines for the creation of Large Scale Dialectal Arabic Annotations](http://www.lrec-conf.org/proceedings/lrec2012/pdf/815_Paper.pdf) (Elfardy & Diab, LREC 2012)
ACL