@inproceedings{al-sabbagh-girju-2010-mining,
title = "Mining the Web for the Induction of a Dialectical {A}rabic Lexicon",
author = "Al-Sabbagh, Rania and
Girju, Roxana",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/344_Paper.pdf",
abstract = "This paper describes the first phase of building a lexicon of Egyptian Cairene Arabic (ECA) ― one of the most widely understood dialects in the Arab World ― and Modern Standard Arabic (MSA). Each ECA entry is mapped to its MSA synonym, Part-of-Speech (POS) tag and top-ranked contexts based on Web queries; and thus each entry is provided with basic syntactic and semantic information for a generic lexicon compatible with multiple NLP applications. Moreover, through their MSA synonyms, ECA entries acquire access to MSA available NLP tools and resources which are considerably available. Using an associationist approach based on the correlations between word co-occurrence patterns in both dialects, we change the direction of the acquisition process from parallel to circular to overcome a bottleneck of current research on Arabic dialects, namely the lack of parallel corpora, and to alleviate accuracy rates for using unrelated Web documents which are more frequently available. Manually evaluated for 1,000 word entries by two native speakers of the ECA-MSA varieties, the proposed approach achieves a promising F-measured performance rate of 70.9{\%}. In discussion to the proposed algorithm, different semantic issues are highlighted for upcoming phases of the induction of a more comprehensive ECA-MSA lexicon.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-sabbagh-girju-2010-mining">
<titleInfo>
<title>Mining the Web for the Induction of a Dialectical Arabic Lexicon</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>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the first phase of building a lexicon of Egyptian Cairene Arabic (ECA) ― one of the most widely understood dialects in the Arab World ― and Modern Standard Arabic (MSA). Each ECA entry is mapped to its MSA synonym, Part-of-Speech (POS) tag and top-ranked contexts based on Web queries; and thus each entry is provided with basic syntactic and semantic information for a generic lexicon compatible with multiple NLP applications. Moreover, through their MSA synonyms, ECA entries acquire access to MSA available NLP tools and resources which are considerably available. Using an associationist approach based on the correlations between word co-occurrence patterns in both dialects, we change the direction of the acquisition process from parallel to circular to overcome a bottleneck of current research on Arabic dialects, namely the lack of parallel corpora, and to alleviate accuracy rates for using unrelated Web documents which are more frequently available. Manually evaluated for 1,000 word entries by two native speakers of the ECA-MSA varieties, the proposed approach achieves a promising F-measured performance rate of 70.9%. In discussion to the proposed algorithm, different semantic issues are highlighted for upcoming phases of the induction of a more comprehensive ECA-MSA lexicon.</abstract>
<identifier type="citekey">al-sabbagh-girju-2010-mining</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/344_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mining the Web for the Induction of a Dialectical Arabic Lexicon
%A Al-Sabbagh, Rania
%A Girju, Roxana
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F al-sabbagh-girju-2010-mining
%X This paper describes the first phase of building a lexicon of Egyptian Cairene Arabic (ECA) ― one of the most widely understood dialects in the Arab World ― and Modern Standard Arabic (MSA). Each ECA entry is mapped to its MSA synonym, Part-of-Speech (POS) tag and top-ranked contexts based on Web queries; and thus each entry is provided with basic syntactic and semantic information for a generic lexicon compatible with multiple NLP applications. Moreover, through their MSA synonyms, ECA entries acquire access to MSA available NLP tools and resources which are considerably available. Using an associationist approach based on the correlations between word co-occurrence patterns in both dialects, we change the direction of the acquisition process from parallel to circular to overcome a bottleneck of current research on Arabic dialects, namely the lack of parallel corpora, and to alleviate accuracy rates for using unrelated Web documents which are more frequently available. Manually evaluated for 1,000 word entries by two native speakers of the ECA-MSA varieties, the proposed approach achieves a promising F-measured performance rate of 70.9%. In discussion to the proposed algorithm, different semantic issues are highlighted for upcoming phases of the induction of a more comprehensive ECA-MSA lexicon.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/344_Paper.pdf
Markdown (Informal)
[Mining the Web for the Induction of a Dialectical Arabic Lexicon](http://www.lrec-conf.org/proceedings/lrec2010/pdf/344_Paper.pdf) (Al-Sabbagh & Girju, LREC 2010)
ACL