@inproceedings{rytting-etal-2010-error,
title = "Error Correction for {A}rabic Dictionary Lookup",
author = "Rytting, C. Anton and
Rodrigues, Paul and
Buckwalter, Tim and
Zajic, David and
Hirsch, Bridget and
Carnes, Jeff and
Lynn, Nathanael and
Wayland, Sarah and
Taylor, Chris and
White, Jason and
Blake III, Charles and
Browne, Evelyn and
Miller, Corey and
Purvis, Tristan",
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/440_Paper.pdf",
abstract = "We describe a new Arabic spelling correction system which is intended for use with electronic dictionary search by learners of Arabic. Unlike other spelling correction systems, this system does not depend on a corpus of attested student errors but on student- and teacher-generated ratings of confusable pairs of phonemes or letters. Separate error modules for keyboard mistypings, phonetic confusions, and dialectal confusions are combined to create a weighted finite-state transducer that calculates the likelihood that an input string could correspond to each citation form in a dictionary of Iraqi Arabic. Results are ranked by the estimated likelihood that a citation form could be misheard, mistyped, or mistranscribed for the input given by the user. To evaluate the system, we developed a noisy-channel model trained on students speech errors and use it to perturb citation forms from a dictionary. We compare our system to a baseline based on Levenshtein distance and find that, when evaluated on single-error queries, our system performs 28{\%} better than the baseline (overall MRR) and is twice as good at returning the correct dictionary form as the top-ranked result. We believe this to be the first spelling correction system designed for a spoken, colloquial dialect of Arabic.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rytting-etal-2010-error">
<titleInfo>
<title>Error Correction for Arabic Dictionary Lookup</title>
</titleInfo>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">Anton</namePart>
<namePart type="family">Rytting</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rodrigues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Buckwalter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Zajic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bridget</namePart>
<namePart type="family">Hirsch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeff</namePart>
<namePart type="family">Carnes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathanael</namePart>
<namePart type="family">Lynn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Wayland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Taylor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">White</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charles</namePart>
<namePart type="family">Blake III</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evelyn</namePart>
<namePart type="family">Browne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Corey</namePart>
<namePart type="family">Miller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Purvis</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>We describe a new Arabic spelling correction system which is intended for use with electronic dictionary search by learners of Arabic. Unlike other spelling correction systems, this system does not depend on a corpus of attested student errors but on student- and teacher-generated ratings of confusable pairs of phonemes or letters. Separate error modules for keyboard mistypings, phonetic confusions, and dialectal confusions are combined to create a weighted finite-state transducer that calculates the likelihood that an input string could correspond to each citation form in a dictionary of Iraqi Arabic. Results are ranked by the estimated likelihood that a citation form could be misheard, mistyped, or mistranscribed for the input given by the user. To evaluate the system, we developed a noisy-channel model trained on students speech errors and use it to perturb citation forms from a dictionary. We compare our system to a baseline based on Levenshtein distance and find that, when evaluated on single-error queries, our system performs 28% better than the baseline (overall MRR) and is twice as good at returning the correct dictionary form as the top-ranked result. We believe this to be the first spelling correction system designed for a spoken, colloquial dialect of Arabic.</abstract>
<identifier type="citekey">rytting-etal-2010-error</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/440_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Error Correction for Arabic Dictionary Lookup
%A Rytting, C. Anton
%A Rodrigues, Paul
%A Buckwalter, Tim
%A Zajic, David
%A Hirsch, Bridget
%A Carnes, Jeff
%A Lynn, Nathanael
%A Wayland, Sarah
%A Taylor, Chris
%A White, Jason
%A Blake III, Charles
%A Browne, Evelyn
%A Miller, Corey
%A Purvis, Tristan
%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 rytting-etal-2010-error
%X We describe a new Arabic spelling correction system which is intended for use with electronic dictionary search by learners of Arabic. Unlike other spelling correction systems, this system does not depend on a corpus of attested student errors but on student- and teacher-generated ratings of confusable pairs of phonemes or letters. Separate error modules for keyboard mistypings, phonetic confusions, and dialectal confusions are combined to create a weighted finite-state transducer that calculates the likelihood that an input string could correspond to each citation form in a dictionary of Iraqi Arabic. Results are ranked by the estimated likelihood that a citation form could be misheard, mistyped, or mistranscribed for the input given by the user. To evaluate the system, we developed a noisy-channel model trained on students speech errors and use it to perturb citation forms from a dictionary. We compare our system to a baseline based on Levenshtein distance and find that, when evaluated on single-error queries, our system performs 28% better than the baseline (overall MRR) and is twice as good at returning the correct dictionary form as the top-ranked result. We believe this to be the first spelling correction system designed for a spoken, colloquial dialect of Arabic.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/440_Paper.pdf
Markdown (Informal)
[Error Correction for Arabic Dictionary Lookup](http://www.lrec-conf.org/proceedings/lrec2010/pdf/440_Paper.pdf) (Rytting et al., LREC 2010)
ACL
- C. Anton Rytting, Paul Rodrigues, Tim Buckwalter, David Zajic, Bridget Hirsch, Jeff Carnes, Nathanael Lynn, Sarah Wayland, Chris Taylor, Jason White, Charles Blake III, Evelyn Browne, Corey Miller, and Tristan Purvis. 2010. Error Correction for Arabic Dictionary Lookup. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).