@inproceedings{hana-etal-2012-building,
title = "Building a learner corpus",
author = {Hana, Jirka and
Rosen, Alexandr and
{\v{S}}tindlov{\'a}, Barbora and
J{\"a}ger, Petr},
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/992_Paper.pdf",
pages = "3228--3232",
abstract = "The paper describes a corpus of texts produced by non-native speakers of Czech. We discuss its annotation scheme, consisting of three interlinked levels to cope with a wide range of error types present in the input. Each level corrects different types of errors; links between the levels allow capturing errors in word order and complex discontinuous expressions. Errors are not only corrected, but also classified. The annotation scheme is tested on a doubly-annotated sample of approx. 10,000 words with fair inter-annotator agreement results. We also explore options of application of automated linguistic annotation tools (taggers, spell checkers and grammar checkers) on the learner text to support or even substitute manual annotation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hana-etal-2012-building">
<titleInfo>
<title>Building a learner corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jirka</namePart>
<namePart type="family">Hana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandr</namePart>
<namePart type="family">Rosen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbora</namePart>
<namePart type="family">Štindlová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petr</namePart>
<namePart type="family">Jäger</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>The paper describes a corpus of texts produced by non-native speakers of Czech. We discuss its annotation scheme, consisting of three interlinked levels to cope with a wide range of error types present in the input. Each level corrects different types of errors; links between the levels allow capturing errors in word order and complex discontinuous expressions. Errors are not only corrected, but also classified. The annotation scheme is tested on a doubly-annotated sample of approx. 10,000 words with fair inter-annotator agreement results. We also explore options of application of automated linguistic annotation tools (taggers, spell checkers and grammar checkers) on the learner text to support or even substitute manual annotation.</abstract>
<identifier type="citekey">hana-etal-2012-building</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/992_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3228</start>
<end>3232</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a learner corpus
%A Hana, Jirka
%A Rosen, Alexandr
%A Štindlová, Barbora
%A Jäger, Petr
%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 hana-etal-2012-building
%X The paper describes a corpus of texts produced by non-native speakers of Czech. We discuss its annotation scheme, consisting of three interlinked levels to cope with a wide range of error types present in the input. Each level corrects different types of errors; links between the levels allow capturing errors in word order and complex discontinuous expressions. Errors are not only corrected, but also classified. The annotation scheme is tested on a doubly-annotated sample of approx. 10,000 words with fair inter-annotator agreement results. We also explore options of application of automated linguistic annotation tools (taggers, spell checkers and grammar checkers) on the learner text to support or even substitute manual annotation.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/992_Paper.pdf
%P 3228-3232
Markdown (Informal)
[Building a learner corpus](http://www.lrec-conf.org/proceedings/lrec2012/pdf/992_Paper.pdf) (Hana et al., LREC 2012)
ACL
- Jirka Hana, Alexandr Rosen, Barbora Štindlová, and Petr Jäger. 2012. Building a learner corpus. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 3228–3232, Istanbul, Turkey. European Language Resources Association (ELRA).