@inproceedings{rosner-etal-2012-incorporating,
title = "Incorporating an Error Corpus into a Spellchecker for {M}altese",
author = "Rosner, Michael and
Gatt, Albert and
Attard, Andrew and
Joachimsen, Jan",
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/1040_Paper.pdf",
pages = "743--750",
abstract = "This paper discusses the ongoing development of a new Maltese spell checker, highlighting the methodologies which would best suit such a language. We thus discuss several previous attempts, highlighting what we believe to be their weakest point: a lack of attention to context. Two developments are of particular interest, both of which concern the availability of language resources relevant to spellchecking: (i) the Maltese Language Resource Server (MLRS) which now includes a representative corpus of c. 100M words extracted from diverse documents including the Maltese Legislation, press releases and extracts from Maltese web-pages and (ii) an extensive and detailed corpus of spelling errors that was collected whilst part of the MLRS texts were being prepared. We describe the structure of these resources as well as the experimental approaches focused on context that we are now in a position to adopt. We describe the framework within which a variety of different approaches to spellchecking and evaluation will be carried out, and briefly discuss the first baseline system we have implemented. We conclude the paper with a roadmap for future improvements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rosner-etal-2012-incorporating">
<titleInfo>
<title>Incorporating an Error Corpus into a Spellchecker for Maltese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="family">Gatt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Attard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Joachimsen</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 paper discusses the ongoing development of a new Maltese spell checker, highlighting the methodologies which would best suit such a language. We thus discuss several previous attempts, highlighting what we believe to be their weakest point: a lack of attention to context. Two developments are of particular interest, both of which concern the availability of language resources relevant to spellchecking: (i) the Maltese Language Resource Server (MLRS) which now includes a representative corpus of c. 100M words extracted from diverse documents including the Maltese Legislation, press releases and extracts from Maltese web-pages and (ii) an extensive and detailed corpus of spelling errors that was collected whilst part of the MLRS texts were being prepared. We describe the structure of these resources as well as the experimental approaches focused on context that we are now in a position to adopt. We describe the framework within which a variety of different approaches to spellchecking and evaluation will be carried out, and briefly discuss the first baseline system we have implemented. We conclude the paper with a roadmap for future improvements.</abstract>
<identifier type="citekey">rosner-etal-2012-incorporating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1040_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>743</start>
<end>750</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incorporating an Error Corpus into a Spellchecker for Maltese
%A Rosner, Michael
%A Gatt, Albert
%A Attard, Andrew
%A Joachimsen, Jan
%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 rosner-etal-2012-incorporating
%X This paper discusses the ongoing development of a new Maltese spell checker, highlighting the methodologies which would best suit such a language. We thus discuss several previous attempts, highlighting what we believe to be their weakest point: a lack of attention to context. Two developments are of particular interest, both of which concern the availability of language resources relevant to spellchecking: (i) the Maltese Language Resource Server (MLRS) which now includes a representative corpus of c. 100M words extracted from diverse documents including the Maltese Legislation, press releases and extracts from Maltese web-pages and (ii) an extensive and detailed corpus of spelling errors that was collected whilst part of the MLRS texts were being prepared. We describe the structure of these resources as well as the experimental approaches focused on context that we are now in a position to adopt. We describe the framework within which a variety of different approaches to spellchecking and evaluation will be carried out, and briefly discuss the first baseline system we have implemented. We conclude the paper with a roadmap for future improvements.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1040_Paper.pdf
%P 743-750
Markdown (Informal)
[Incorporating an Error Corpus into a Spellchecker for Maltese](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1040_Paper.pdf) (Rosner et al., LREC 2012)
ACL
- Michael Rosner, Albert Gatt, Andrew Attard, and Jan Joachimsen. 2012. Incorporating an Error Corpus into a Spellchecker for Maltese. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 743–750, Istanbul, Turkey. European Language Resources Association (ELRA).