@inproceedings{sawalha-atwell-2010-fine,
title = "Fine-Grain Morphological Analyzer and Part-of-Speech Tagger for {A}rabic Text",
author = "Sawalha, Majdi and
Atwell, Eric",
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/282_Paper.pdf",
abstract = "Morphological analyzers and part-of-speech taggers are key technologies for most text analysis applications. Our aim is to develop a part-of-speech tagger for annotating a wide range of Arabic text formats, domains and genres including both vowelized and non-vowelized text. Enriching the text with linguistic analysis will maximize the potential for corpus re-use in a wide range of applications. We foresee the advantage of enriching the text with part-of-speech tags of very fine-grained grammatical distinctions, which reflect expert interest in syntax and morphology, but not specific needs of end-users, because end-user applications are not known in advance. In this paper we review existing Arabic Part-of-Speech Taggers and tag-sets, and illustrate four different Arabic PoS tag-sets for a sample of Arabic text from the Quran. We describe the detailed fine-grained morphological feature tag set of Arabic, and the fine-grained Arabic morphological analyzer algorithm. We faced practical challenges in applying the morphological analyzer to the 100-million-word Web Arabic Corpus: we had to port the software to the National Grid Service, adapt the analyser to cope with spelling variations and errors, and utilise a Broad-Coverage Lexical Resource combining 23 traditional Arabic lexicons. Finally we outline the construction of a Gold Standard for comparative evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sawalha-atwell-2010-fine">
<titleInfo>
<title>Fine-Grain Morphological Analyzer and Part-of-Speech Tagger for Arabic Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Majdi</namePart>
<namePart type="family">Sawalha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Atwell</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>Morphological analyzers and part-of-speech taggers are key technologies for most text analysis applications. Our aim is to develop a part-of-speech tagger for annotating a wide range of Arabic text formats, domains and genres including both vowelized and non-vowelized text. Enriching the text with linguistic analysis will maximize the potential for corpus re-use in a wide range of applications. We foresee the advantage of enriching the text with part-of-speech tags of very fine-grained grammatical distinctions, which reflect expert interest in syntax and morphology, but not specific needs of end-users, because end-user applications are not known in advance. In this paper we review existing Arabic Part-of-Speech Taggers and tag-sets, and illustrate four different Arabic PoS tag-sets for a sample of Arabic text from the Quran. We describe the detailed fine-grained morphological feature tag set of Arabic, and the fine-grained Arabic morphological analyzer algorithm. We faced practical challenges in applying the morphological analyzer to the 100-million-word Web Arabic Corpus: we had to port the software to the National Grid Service, adapt the analyser to cope with spelling variations and errors, and utilise a Broad-Coverage Lexical Resource combining 23 traditional Arabic lexicons. Finally we outline the construction of a Gold Standard for comparative evaluation.</abstract>
<identifier type="citekey">sawalha-atwell-2010-fine</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/282_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-Grain Morphological Analyzer and Part-of-Speech Tagger for Arabic Text
%A Sawalha, Majdi
%A Atwell, Eric
%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 sawalha-atwell-2010-fine
%X Morphological analyzers and part-of-speech taggers are key technologies for most text analysis applications. Our aim is to develop a part-of-speech tagger for annotating a wide range of Arabic text formats, domains and genres including both vowelized and non-vowelized text. Enriching the text with linguistic analysis will maximize the potential for corpus re-use in a wide range of applications. We foresee the advantage of enriching the text with part-of-speech tags of very fine-grained grammatical distinctions, which reflect expert interest in syntax and morphology, but not specific needs of end-users, because end-user applications are not known in advance. In this paper we review existing Arabic Part-of-Speech Taggers and tag-sets, and illustrate four different Arabic PoS tag-sets for a sample of Arabic text from the Quran. We describe the detailed fine-grained morphological feature tag set of Arabic, and the fine-grained Arabic morphological analyzer algorithm. We faced practical challenges in applying the morphological analyzer to the 100-million-word Web Arabic Corpus: we had to port the software to the National Grid Service, adapt the analyser to cope with spelling variations and errors, and utilise a Broad-Coverage Lexical Resource combining 23 traditional Arabic lexicons. Finally we outline the construction of a Gold Standard for comparative evaluation.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/282_Paper.pdf
Markdown (Informal)
[Fine-Grain Morphological Analyzer and Part-of-Speech Tagger for Arabic Text](http://www.lrec-conf.org/proceedings/lrec2010/pdf/282_Paper.pdf) (Sawalha & Atwell, LREC 2010)
ACL