@inproceedings{katinskaia-etal-2022-semi,
title = "Semi-automatically Annotated Learner Corpus for {R}ussian",
author = "Katinskaia, Anisia and
Lebedeva, Maria and
Hou, Jue and
Yangarber, Roman",
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-1.88",
pages = "832--839",
abstract = "We present ReLCo{---} the Revita Learner Corpus{---}a new semi-automatically annotated learner corpus for Russian. The corpus was collected while several thousand L2 learners were performing exercises using the Revita language-learning system. All errors were detected automatically by the system and annotated by type. Part of the corpus was annotated manually{---}this part was created for further experiments on automatic assessment of grammatical correctness. The Learner Corpus provides valuable data for studying patterns of grammatical errors, experimenting with grammatical error detection and grammatical error correction, and developing new exercises for language learners. Automating the collection and annotation makes the process of building the learner corpus much cheaper and faster, in contrast to the traditional approach of building learner corpora. We make the data publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="katinskaia-etal-2022-semi">
<titleInfo>
<title>Semi-automatically Annotated Learner Corpus for Russian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anisia</namePart>
<namePart type="family">Katinskaia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Lebedeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jue</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</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>We present ReLCo— the Revita Learner Corpus—a new semi-automatically annotated learner corpus for Russian. The corpus was collected while several thousand L2 learners were performing exercises using the Revita language-learning system. All errors were detected automatically by the system and annotated by type. Part of the corpus was annotated manually—this part was created for further experiments on automatic assessment of grammatical correctness. The Learner Corpus provides valuable data for studying patterns of grammatical errors, experimenting with grammatical error detection and grammatical error correction, and developing new exercises for language learners. Automating the collection and annotation makes the process of building the learner corpus much cheaper and faster, in contrast to the traditional approach of building learner corpora. We make the data publicly available.</abstract>
<identifier type="citekey">katinskaia-etal-2022-semi</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.88</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>832</start>
<end>839</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semi-automatically Annotated Learner Corpus for Russian
%A Katinskaia, Anisia
%A Lebedeva, Maria
%A Hou, Jue
%A Yangarber, Roman
%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 katinskaia-etal-2022-semi
%X We present ReLCo— the Revita Learner Corpus—a new semi-automatically annotated learner corpus for Russian. The corpus was collected while several thousand L2 learners were performing exercises using the Revita language-learning system. All errors were detected automatically by the system and annotated by type. Part of the corpus was annotated manually—this part was created for further experiments on automatic assessment of grammatical correctness. The Learner Corpus provides valuable data for studying patterns of grammatical errors, experimenting with grammatical error detection and grammatical error correction, and developing new exercises for language learners. Automating the collection and annotation makes the process of building the learner corpus much cheaper and faster, in contrast to the traditional approach of building learner corpora. We make the data publicly available.
%U https://aclanthology.org/2022.lrec-1.88
%P 832-839
Markdown (Informal)
[Semi-automatically Annotated Learner Corpus for Russian](https://aclanthology.org/2022.lrec-1.88) (Katinskaia et al., LREC 2022)
ACL
- Anisia Katinskaia, Maria Lebedeva, Jue Hou, and Roman Yangarber. 2022. Semi-automatically Annotated Learner Corpus for Russian. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 832–839, Marseille, France. European Language Resources Association.