@inproceedings{atserias-etal-2012-spell,
title = "Spell Checking in {S}panish: The Case of Diacritic Accents",
author = "Atserias, Jordi and
Fuentes, Maria and
Nazar, Rogelio and
Renau, Irene",
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/754_Paper.pdf",
pages = "737--742",
abstract = "This article presents the problem of diacritic restoration (or diacritization) in the context of spell-checking, with the focus on an orthographically rich language such as Spanish. We argue that despite the large volume of work published on the topic of diacritization, currently available spell-checking tools have still not found a proper solution to the problem in those cases where both forms of a word are listed in the checker's dictionary. This is the case, for instance, when a word form exists with and without diacritics, such as continuo continuous' and continu{\'o} he/she/it continued', or when different diacritics make other word distinctions, as in contin{\'u}o I continue'. We propose a very simple solution based on a word bigram model derived from correctly typed Spanish texts and evaluate the ability of this model to restore diacritics in artificial as well as real errors. The case of diacritics is only meant to be an example of the possible applications for this idea, yet we believe that the same method could be applied to other kinds of orthographic or even grammatical errors. Moreover, given that no explicit linguistic knowledge is required, the proposed model can be used with other languages provided that a large normative corpus is available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="atserias-etal-2012-spell">
<titleInfo>
<title>Spell Checking in Spanish: The Case of Diacritic Accents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jordi</namePart>
<namePart type="family">Atserias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Fuentes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rogelio</namePart>
<namePart type="family">Nazar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irene</namePart>
<namePart type="family">Renau</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>This article presents the problem of diacritic restoration (or diacritization) in the context of spell-checking, with the focus on an orthographically rich language such as Spanish. We argue that despite the large volume of work published on the topic of diacritization, currently available spell-checking tools have still not found a proper solution to the problem in those cases where both forms of a word are listed in the checker’s dictionary. This is the case, for instance, when a word form exists with and without diacritics, such as continuo continuous’ and continuó he/she/it continued’, or when different diacritics make other word distinctions, as in continúo I continue’. We propose a very simple solution based on a word bigram model derived from correctly typed Spanish texts and evaluate the ability of this model to restore diacritics in artificial as well as real errors. The case of diacritics is only meant to be an example of the possible applications for this idea, yet we believe that the same method could be applied to other kinds of orthographic or even grammatical errors. Moreover, given that no explicit linguistic knowledge is required, the proposed model can be used with other languages provided that a large normative corpus is available.</abstract>
<identifier type="citekey">atserias-etal-2012-spell</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/754_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>737</start>
<end>742</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spell Checking in Spanish: The Case of Diacritic Accents
%A Atserias, Jordi
%A Fuentes, Maria
%A Nazar, Rogelio
%A Renau, Irene
%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 atserias-etal-2012-spell
%X This article presents the problem of diacritic restoration (or diacritization) in the context of spell-checking, with the focus on an orthographically rich language such as Spanish. We argue that despite the large volume of work published on the topic of diacritization, currently available spell-checking tools have still not found a proper solution to the problem in those cases where both forms of a word are listed in the checker’s dictionary. This is the case, for instance, when a word form exists with and without diacritics, such as continuo continuous’ and continuó he/she/it continued’, or when different diacritics make other word distinctions, as in continúo I continue’. We propose a very simple solution based on a word bigram model derived from correctly typed Spanish texts and evaluate the ability of this model to restore diacritics in artificial as well as real errors. The case of diacritics is only meant to be an example of the possible applications for this idea, yet we believe that the same method could be applied to other kinds of orthographic or even grammatical errors. Moreover, given that no explicit linguistic knowledge is required, the proposed model can be used with other languages provided that a large normative corpus is available.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/754_Paper.pdf
%P 737-742
Markdown (Informal)
[Spell Checking in Spanish: The Case of Diacritic Accents](http://www.lrec-conf.org/proceedings/lrec2012/pdf/754_Paper.pdf) (Atserias et al., LREC 2012)
ACL
- Jordi Atserias, Maria Fuentes, Rogelio Nazar, and Irene Renau. 2012. Spell Checking in Spanish: The Case of Diacritic Accents. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 737–742, Istanbul, Turkey. European Language Resources Association (ELRA).