@inproceedings{dargis-etal-2020-quality,
title = "Quality Focused Approach to a Learner Corpus Development",
author = "Dar{\c{g}}is, Roberts and
Auzi{\c{n}}a, Ilze and
Lev{\=a}ne-Petrova, Krist{\=\i}ne and
Kaija, Inga",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.49",
pages = "392--396",
abstract = "The paper presents quality focused approach to a learner corpus development. The methodology was developed with multiple design considerations put in place to make the annotation process easier and at the same time reduce the amount of mistakes that could be introduced due to inconsistent text correction or carelessness. The approach suggested in this paper consists of multiple parts: comparison of digitized texts by several annotators, text correction, automated morphological analysis, and manual review of annotations. The described approach is used to create Latvian Language Learner corpus (LaVA) which is part of a currently ongoing project Development of Learner corpus of Latvian: methods, tools and applications.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dargis-etal-2020-quality">
<titleInfo>
<title>Quality Focused Approach to a Learner Corpus Development</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roberts</namePart>
<namePart type="family">Darģis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilze</namePart>
<namePart type="family">Auziņa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristīne</namePart>
<namePart type="family">Levāne-Petrova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inga</namePart>
<namePart type="family">Kaija</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>The paper presents quality focused approach to a learner corpus development. The methodology was developed with multiple design considerations put in place to make the annotation process easier and at the same time reduce the amount of mistakes that could be introduced due to inconsistent text correction or carelessness. The approach suggested in this paper consists of multiple parts: comparison of digitized texts by several annotators, text correction, automated morphological analysis, and manual review of annotations. The described approach is used to create Latvian Language Learner corpus (LaVA) which is part of a currently ongoing project Development of Learner corpus of Latvian: methods, tools and applications.</abstract>
<identifier type="citekey">dargis-etal-2020-quality</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.49</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>392</start>
<end>396</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quality Focused Approach to a Learner Corpus Development
%A Darģis, Roberts
%A Auziņa, Ilze
%A Levāne-Petrova, Kristīne
%A Kaija, Inga
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F dargis-etal-2020-quality
%X The paper presents quality focused approach to a learner corpus development. The methodology was developed with multiple design considerations put in place to make the annotation process easier and at the same time reduce the amount of mistakes that could be introduced due to inconsistent text correction or carelessness. The approach suggested in this paper consists of multiple parts: comparison of digitized texts by several annotators, text correction, automated morphological analysis, and manual review of annotations. The described approach is used to create Latvian Language Learner corpus (LaVA) which is part of a currently ongoing project Development of Learner corpus of Latvian: methods, tools and applications.
%U https://aclanthology.org/2020.lrec-1.49
%P 392-396
Markdown (Informal)
[Quality Focused Approach to a Learner Corpus Development](https://aclanthology.org/2020.lrec-1.49) (Darģis et al., LREC 2020)
ACL
- Roberts Darģis, Ilze Auziņa, Kristīne Levāne-Petrova, and Inga Kaija. 2020. Quality Focused Approach to a Learner Corpus Development. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 392–396, Marseille, France. European Language Resources Association.