@inproceedings{pedler-mitton-2010-large,
title = "A Large List of Confusion Sets for Spellchecking Assessed Against a Corpus of Real-word Errors",
author = "Pedler, Jennifer and
Mitton, Roger",
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/122_Paper.pdf",
abstract = "One of the methods that has been proposed for dealing with real-word errors (errors that occur when a correctly spelled word is substituted for the one intended) is the ''``confusion-set'''' approach - a confusion set being a small group of words that are likely to be confused with one another. Using a list of confusion sets drawn up in advance, a spellchecker, on finding one of these words in a text, can assess whether one of the other members of its set would be a better fit and, if it appears to be so, propose that word as a correction. Much of the research using this approach has suffered from two weaknesses. The first is the small number of confusion sets used. The second is that systems have largely been tested on artificial errors. In this paper we address these two weaknesses. We describe the creation of a realistically sized list of confusion sets, then the assembling of a corpus of real-word errors, and then we assess the potential of that list in relation to that corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pedler-mitton-2010-large">
<titleInfo>
<title>A Large List of Confusion Sets for Spellchecking Assessed Against a Corpus of Real-word Errors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Pedler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roger</namePart>
<namePart type="family">Mitton</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>One of the methods that has been proposed for dealing with real-word errors (errors that occur when a correctly spelled word is substituted for the one intended) is the ”“confusion-set”” approach - a confusion set being a small group of words that are likely to be confused with one another. Using a list of confusion sets drawn up in advance, a spellchecker, on finding one of these words in a text, can assess whether one of the other members of its set would be a better fit and, if it appears to be so, propose that word as a correction. Much of the research using this approach has suffered from two weaknesses. The first is the small number of confusion sets used. The second is that systems have largely been tested on artificial errors. In this paper we address these two weaknesses. We describe the creation of a realistically sized list of confusion sets, then the assembling of a corpus of real-word errors, and then we assess the potential of that list in relation to that corpus.</abstract>
<identifier type="citekey">pedler-mitton-2010-large</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/122_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Large List of Confusion Sets for Spellchecking Assessed Against a Corpus of Real-word Errors
%A Pedler, Jennifer
%A Mitton, Roger
%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 pedler-mitton-2010-large
%X One of the methods that has been proposed for dealing with real-word errors (errors that occur when a correctly spelled word is substituted for the one intended) is the ”“confusion-set”” approach - a confusion set being a small group of words that are likely to be confused with one another. Using a list of confusion sets drawn up in advance, a spellchecker, on finding one of these words in a text, can assess whether one of the other members of its set would be a better fit and, if it appears to be so, propose that word as a correction. Much of the research using this approach has suffered from two weaknesses. The first is the small number of confusion sets used. The second is that systems have largely been tested on artificial errors. In this paper we address these two weaknesses. We describe the creation of a realistically sized list of confusion sets, then the assembling of a corpus of real-word errors, and then we assess the potential of that list in relation to that corpus.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/122_Paper.pdf
Markdown (Informal)
[A Large List of Confusion Sets for Spellchecking Assessed Against a Corpus of Real-word Errors](http://www.lrec-conf.org/proceedings/lrec2010/pdf/122_Paper.pdf) (Pedler & Mitton, LREC 2010)
ACL