@inproceedings{megyesi-etal-2016-uppsala,
title = "The {U}ppsala Corpus of Student Writings: Corpus Creation, Annotation, and Analysis",
author = {Megyesi, Be{\'a}ta and
N{\"a}sman, Jesper and
Palm{\'e}r, Anne},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1509",
pages = "3192--3199",
abstract = "The Uppsala Corpus of Student Writings consists of Swedish texts produced as part of a national test of students ranging in age from nine (in year three of primary school) to nineteen (the last year of upper secondary school) who are studying either Swedish or Swedish as a second language. National tests have been collected since 1996. The corpus currently consists of 2,500 texts containing over 1.5 million tokens. Parts of the texts have been annotated on several linguistic levels using existing state-of-the-art natural language processing tools. In order to make the corpus easy to interpret for scholars in the humanities, we chose the CoNLL format instead of an XML-based representation. Since spelling and grammatical errors are common in student writings, the texts are automatically corrected while keeping the original tokens in the corpus. Each token is annotated with part-of-speech and morphological features as well as syntactic structure. The main purpose of the corpus is to facilitate the systematic and quantitative empirical study of the writings of various student groups based on gender, geographic area, age, grade awarded or a combination of these, synchronically or diachronically. The intention is for this to be a monitor corpus, currently under development.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="megyesi-etal-2016-uppsala">
<titleInfo>
<title>The Uppsala Corpus of Student Writings: Corpus Creation, Annotation, and Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Beáta</namePart>
<namePart type="family">Megyesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesper</namePart>
<namePart type="family">Näsman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Palmér</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Uppsala Corpus of Student Writings consists of Swedish texts produced as part of a national test of students ranging in age from nine (in year three of primary school) to nineteen (the last year of upper secondary school) who are studying either Swedish or Swedish as a second language. National tests have been collected since 1996. The corpus currently consists of 2,500 texts containing over 1.5 million tokens. Parts of the texts have been annotated on several linguistic levels using existing state-of-the-art natural language processing tools. In order to make the corpus easy to interpret for scholars in the humanities, we chose the CoNLL format instead of an XML-based representation. Since spelling and grammatical errors are common in student writings, the texts are automatically corrected while keeping the original tokens in the corpus. Each token is annotated with part-of-speech and morphological features as well as syntactic structure. The main purpose of the corpus is to facilitate the systematic and quantitative empirical study of the writings of various student groups based on gender, geographic area, age, grade awarded or a combination of these, synchronically or diachronically. The intention is for this to be a monitor corpus, currently under development.</abstract>
<identifier type="citekey">megyesi-etal-2016-uppsala</identifier>
<location>
<url>https://aclanthology.org/L16-1509</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3192</start>
<end>3199</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Uppsala Corpus of Student Writings: Corpus Creation, Annotation, and Analysis
%A Megyesi, Beáta
%A Näsman, Jesper
%A Palmér, Anne
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F megyesi-etal-2016-uppsala
%X The Uppsala Corpus of Student Writings consists of Swedish texts produced as part of a national test of students ranging in age from nine (in year three of primary school) to nineteen (the last year of upper secondary school) who are studying either Swedish or Swedish as a second language. National tests have been collected since 1996. The corpus currently consists of 2,500 texts containing over 1.5 million tokens. Parts of the texts have been annotated on several linguistic levels using existing state-of-the-art natural language processing tools. In order to make the corpus easy to interpret for scholars in the humanities, we chose the CoNLL format instead of an XML-based representation. Since spelling and grammatical errors are common in student writings, the texts are automatically corrected while keeping the original tokens in the corpus. Each token is annotated with part-of-speech and morphological features as well as syntactic structure. The main purpose of the corpus is to facilitate the systematic and quantitative empirical study of the writings of various student groups based on gender, geographic area, age, grade awarded or a combination of these, synchronically or diachronically. The intention is for this to be a monitor corpus, currently under development.
%U https://aclanthology.org/L16-1509
%P 3192-3199
Markdown (Informal)
[The Uppsala Corpus of Student Writings: Corpus Creation, Annotation, and Analysis](https://aclanthology.org/L16-1509) (Megyesi et al., LREC 2016)
ACL