@inproceedings{bustamante-diaz-2006-spelling,
title = "Spelling Error Patterns in {S}panish for Word Processing Applications",
author = "Bustamante, Flora Ram{\'\i}rez and
D{\'\i}az, Enrique L{\'o}pez",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/119_pdf.pdf",
abstract = "This paper reports findings from the elaboration of a typology of spelling errors for Spanish. It also discusses previous generalizations about spelling error patterns found in other studies and offers new insights on them. The typology is based on the analysis of around 76K misspellings found in real-life texts produced by humans. The main goal of the elaboration of the typology was to help in the im-plementation of a spell checker that detects context-independent misspellings in general unrestricted texts with the most common con-fusion pairs (i.e. error/correction pairs) to improve the set of ranked correction candidates for misspellings. We found that spelling er-rors are language dependent and are closely related to the orthographic rules of each language. The statistical data we provide on spell-ing error patterns in Spanish and their comparison with other data in other related works are the novel contribution of this paper. In this line, this paper shows that some of the general statements found in the literature about spelling error patterns apply mainly to English and cannot be extrapolated to other languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bustamante-diaz-2006-spelling">
<titleInfo>
<title>Spelling Error Patterns in Spanish for Word Processing Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Flora</namePart>
<namePart type="given">Ramírez</namePart>
<namePart type="family">Bustamante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrique</namePart>
<namePart type="given">López</namePart>
<namePart type="family">Díaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper reports findings from the elaboration of a typology of spelling errors for Spanish. It also discusses previous generalizations about spelling error patterns found in other studies and offers new insights on them. The typology is based on the analysis of around 76K misspellings found in real-life texts produced by humans. The main goal of the elaboration of the typology was to help in the im-plementation of a spell checker that detects context-independent misspellings in general unrestricted texts with the most common con-fusion pairs (i.e. error/correction pairs) to improve the set of ranked correction candidates for misspellings. We found that spelling er-rors are language dependent and are closely related to the orthographic rules of each language. The statistical data we provide on spell-ing error patterns in Spanish and their comparison with other data in other related works are the novel contribution of this paper. In this line, this paper shows that some of the general statements found in the literature about spelling error patterns apply mainly to English and cannot be extrapolated to other languages.</abstract>
<identifier type="citekey">bustamante-diaz-2006-spelling</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/119_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spelling Error Patterns in Spanish for Word Processing Applications
%A Bustamante, Flora Ramírez
%A Díaz, Enrique López
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F bustamante-diaz-2006-spelling
%X This paper reports findings from the elaboration of a typology of spelling errors for Spanish. It also discusses previous generalizations about spelling error patterns found in other studies and offers new insights on them. The typology is based on the analysis of around 76K misspellings found in real-life texts produced by humans. The main goal of the elaboration of the typology was to help in the im-plementation of a spell checker that detects context-independent misspellings in general unrestricted texts with the most common con-fusion pairs (i.e. error/correction pairs) to improve the set of ranked correction candidates for misspellings. We found that spelling er-rors are language dependent and are closely related to the orthographic rules of each language. The statistical data we provide on spell-ing error patterns in Spanish and their comparison with other data in other related works are the novel contribution of this paper. In this line, this paper shows that some of the general statements found in the literature about spelling error patterns apply mainly to English and cannot be extrapolated to other languages.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/119_pdf.pdf
Markdown (Informal)
[Spelling Error Patterns in Spanish for Word Processing Applications](http://www.lrec-conf.org/proceedings/lrec2006/pdf/119_pdf.pdf) (Bustamante & Díaz, LREC 2006)
ACL