@inproceedings{shaalan-etal-2012-arabic,
title = "{A}rabic Word Generation and Modelling for Spell Checking",
author = "Shaalan, Khaled and
Attia, Mohammed and
Pecina, Pavel and
Samih, Younes and
van Genabith, Josef",
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/603_Paper.pdf",
pages = "719--725",
abstract = "Arabic is a language known for its rich and complex morphology. Although many research projects have focused on the problem of Arabic morphological analysis using different techniques and approaches, very few have addressed the issue of generation of fully inflected words for the purpose of text authoring. Available open-source spell checking resources for Arabic are too small and inadequate. Ayaspell, for example, the official resource used with OpenOffice applications, contains only 300,000 fully inflected words. We try to bridge this critical gap by creating an adequate, open-source and large-coverage word list for Arabic containing 9,000,000 fully inflected surface words. Furthermore, from a large list of valid forms and invalid forms we create a character-based tri-gram language model to approximate knowledge about permissible character clusters in Arabic, creating a novel method for detecting spelling errors. Testing of this language model gives a precision of 98.2{\%} at a recall of 100{\%}. We take our research a step further by creating a context-independent spelling correction tool using a finite-state automaton that measures the edit distance between input words and candidate corrections, the Noisy Channel Model, and knowledge-based rules. Our system performs significantly better than Hunspell in choosing the best solution, but it is still below the MS Spell Checker.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shaalan-etal-2012-arabic">
<titleInfo>
<title>Arabic Word Generation and Modelling for Spell Checking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khaled</namePart>
<namePart type="family">Shaalan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Attia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Pecina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younes</namePart>
<namePart type="family">Samih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">van Genabith</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>Arabic is a language known for its rich and complex morphology. Although many research projects have focused on the problem of Arabic morphological analysis using different techniques and approaches, very few have addressed the issue of generation of fully inflected words for the purpose of text authoring. Available open-source spell checking resources for Arabic are too small and inadequate. Ayaspell, for example, the official resource used with OpenOffice applications, contains only 300,000 fully inflected words. We try to bridge this critical gap by creating an adequate, open-source and large-coverage word list for Arabic containing 9,000,000 fully inflected surface words. Furthermore, from a large list of valid forms and invalid forms we create a character-based tri-gram language model to approximate knowledge about permissible character clusters in Arabic, creating a novel method for detecting spelling errors. Testing of this language model gives a precision of 98.2% at a recall of 100%. We take our research a step further by creating a context-independent spelling correction tool using a finite-state automaton that measures the edit distance between input words and candidate corrections, the Noisy Channel Model, and knowledge-based rules. Our system performs significantly better than Hunspell in choosing the best solution, but it is still below the MS Spell Checker.</abstract>
<identifier type="citekey">shaalan-etal-2012-arabic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/603_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>719</start>
<end>725</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic Word Generation and Modelling for Spell Checking
%A Shaalan, Khaled
%A Attia, Mohammed
%A Pecina, Pavel
%A Samih, Younes
%A van Genabith, Josef
%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 shaalan-etal-2012-arabic
%X Arabic is a language known for its rich and complex morphology. Although many research projects have focused on the problem of Arabic morphological analysis using different techniques and approaches, very few have addressed the issue of generation of fully inflected words for the purpose of text authoring. Available open-source spell checking resources for Arabic are too small and inadequate. Ayaspell, for example, the official resource used with OpenOffice applications, contains only 300,000 fully inflected words. We try to bridge this critical gap by creating an adequate, open-source and large-coverage word list for Arabic containing 9,000,000 fully inflected surface words. Furthermore, from a large list of valid forms and invalid forms we create a character-based tri-gram language model to approximate knowledge about permissible character clusters in Arabic, creating a novel method for detecting spelling errors. Testing of this language model gives a precision of 98.2% at a recall of 100%. We take our research a step further by creating a context-independent spelling correction tool using a finite-state automaton that measures the edit distance between input words and candidate corrections, the Noisy Channel Model, and knowledge-based rules. Our system performs significantly better than Hunspell in choosing the best solution, but it is still below the MS Spell Checker.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/603_Paper.pdf
%P 719-725
Markdown (Informal)
[Arabic Word Generation and Modelling for Spell Checking](http://www.lrec-conf.org/proceedings/lrec2012/pdf/603_Paper.pdf) (Shaalan et al., LREC 2012)
ACL
- Khaled Shaalan, Mohammed Attia, Pavel Pecina, Younes Samih, and Josef van Genabith. 2012. Arabic Word Generation and Modelling for Spell Checking. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 719–725, Istanbul, Turkey. European Language Resources Association (ELRA).