@inproceedings{sheykholeslam-etal-2012-framework,
title = "A Framework for Spelling Correction in {P}ersian Language Using Noisy Channel Model",
author = "Sheykholeslam, Mohammad Hoseyn and
Minaei-Bidgoli, Behrouz and
Juzi, Hossein",
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/384_Paper.pdf",
pages = "706--710",
abstract = "There are several methods offered for spelling correction in Farsi (Persian) Language. Unfortunately no powerful framework has been implemented because of lack of a large training set in Farsi as an accurate model. A training set consisting of erroneous and related correction string pairs have been obtained from a large number of instances of the books each of which were typed two times in Computer Research Center of Islamic Sciences. We trained our error model using this huge set. In testing part after finding erroneous words in sample text, our program proposes some candidates for related correction. The paper focuses on describing the method of ranking related corrections. This method is customized version of Noisy Channel Spelling Correction for Farsi. This ranking method attempts to find intended correction c from a typo t, that maximizes P(c) P(t | c). In this paper different methods are described and analyzed to obtain a wide overview of the field. Our evaluation results show that Noisy Channel Model using our corpus and training set in this framework works more accurately and improves efficiently in comparison with other methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sheykholeslam-etal-2012-framework">
<titleInfo>
<title>A Framework for Spelling Correction in Persian Language Using Noisy Channel Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Hoseyn</namePart>
<namePart type="family">Sheykholeslam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Behrouz</namePart>
<namePart type="family">Minaei-Bidgoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hossein</namePart>
<namePart type="family">Juzi</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>There are several methods offered for spelling correction in Farsi (Persian) Language. Unfortunately no powerful framework has been implemented because of lack of a large training set in Farsi as an accurate model. A training set consisting of erroneous and related correction string pairs have been obtained from a large number of instances of the books each of which were typed two times in Computer Research Center of Islamic Sciences. We trained our error model using this huge set. In testing part after finding erroneous words in sample text, our program proposes some candidates for related correction. The paper focuses on describing the method of ranking related corrections. This method is customized version of Noisy Channel Spelling Correction for Farsi. This ranking method attempts to find intended correction c from a typo t, that maximizes P(c) P(t | c). In this paper different methods are described and analyzed to obtain a wide overview of the field. Our evaluation results show that Noisy Channel Model using our corpus and training set in this framework works more accurately and improves efficiently in comparison with other methods.</abstract>
<identifier type="citekey">sheykholeslam-etal-2012-framework</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/384_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>706</start>
<end>710</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Framework for Spelling Correction in Persian Language Using Noisy Channel Model
%A Sheykholeslam, Mohammad Hoseyn
%A Minaei-Bidgoli, Behrouz
%A Juzi, Hossein
%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 sheykholeslam-etal-2012-framework
%X There are several methods offered for spelling correction in Farsi (Persian) Language. Unfortunately no powerful framework has been implemented because of lack of a large training set in Farsi as an accurate model. A training set consisting of erroneous and related correction string pairs have been obtained from a large number of instances of the books each of which were typed two times in Computer Research Center of Islamic Sciences. We trained our error model using this huge set. In testing part after finding erroneous words in sample text, our program proposes some candidates for related correction. The paper focuses on describing the method of ranking related corrections. This method is customized version of Noisy Channel Spelling Correction for Farsi. This ranking method attempts to find intended correction c from a typo t, that maximizes P(c) P(t | c). In this paper different methods are described and analyzed to obtain a wide overview of the field. Our evaluation results show that Noisy Channel Model using our corpus and training set in this framework works more accurately and improves efficiently in comparison with other methods.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/384_Paper.pdf
%P 706-710
Markdown (Informal)
[A Framework for Spelling Correction in Persian Language Using Noisy Channel Model](http://www.lrec-conf.org/proceedings/lrec2012/pdf/384_Paper.pdf) (Sheykholeslam et al., LREC 2012)
ACL