@inproceedings{dargis-etal-2022-lava,
title = "{L}a{VA} {--} {L}atvian Language Learner corpus",
author = "Dar{\c{g}}is, Roberts and
Auzi{\c{n}}a, Ilze and
Kaija, Inga and
Lev{\=a}ne-Petrova, Krist{\=\i}ne and
Pokratniece, Krist{\=\i}ne",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.77",
pages = "727--731",
abstract = "This paper presents the Latvian Language Learner Corpus (LaVA) developed at the Institute of Mathematics and Computer Science, University of Latvia. LaVA corpus contains 1015 essays (190k tokens and 790k characters excluding whitespaces) from foreigners studying at Latvian higher education institutions and who are learning Latvian as a foreign language in the first or second semester, reaching the A1 (possibly A2) Latvian language proficiency level. The corpus has morphological and error annotations. Error analysis and the statistics of the LaVA corpus are also provided in the paper. The corpus is publicly available at: \url{http://www.korpuss.lv/id/LaVA}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dargis-etal-2022-lava">
<titleInfo>
<title>LaVA – Latvian Language Learner corpus</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">Inga</namePart>
<namePart type="family">Kaija</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">Kristīne</namePart>
<namePart type="family">Pokratniece</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>This paper presents the Latvian Language Learner Corpus (LaVA) developed at the Institute of Mathematics and Computer Science, University of Latvia. LaVA corpus contains 1015 essays (190k tokens and 790k characters excluding whitespaces) from foreigners studying at Latvian higher education institutions and who are learning Latvian as a foreign language in the first or second semester, reaching the A1 (possibly A2) Latvian language proficiency level. The corpus has morphological and error annotations. Error analysis and the statistics of the LaVA corpus are also provided in the paper. The corpus is publicly available at: http://www.korpuss.lv/id/LaVA.</abstract>
<identifier type="citekey">dargis-etal-2022-lava</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.77</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>727</start>
<end>731</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LaVA – Latvian Language Learner corpus
%A Darģis, Roberts
%A Auziņa, Ilze
%A Kaija, Inga
%A Levāne-Petrova, Kristīne
%A Pokratniece, Kristīne
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F dargis-etal-2022-lava
%X This paper presents the Latvian Language Learner Corpus (LaVA) developed at the Institute of Mathematics and Computer Science, University of Latvia. LaVA corpus contains 1015 essays (190k tokens and 790k characters excluding whitespaces) from foreigners studying at Latvian higher education institutions and who are learning Latvian as a foreign language in the first or second semester, reaching the A1 (possibly A2) Latvian language proficiency level. The corpus has morphological and error annotations. Error analysis and the statistics of the LaVA corpus are also provided in the paper. The corpus is publicly available at: http://www.korpuss.lv/id/LaVA.
%U https://aclanthology.org/2022.lrec-1.77
%P 727-731
Markdown (Informal)
[LaVA – Latvian Language Learner corpus](https://aclanthology.org/2022.lrec-1.77) (Darģis et al., LREC 2022)
ACL
- Roberts Darģis, Ilze Auziņa, Inga Kaija, Kristīne Levāne-Petrova, and Kristīne Pokratniece. 2022. LaVA – Latvian Language Learner corpus. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 727–731, Marseille, France. European Language Resources Association.