@inproceedings{daudaravicius-2014-language,
title = "Language Editing Dataset of Academic Texts",
author = "Daudaravi{\v{c}}ius, Vidas",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/714_Paper.pdf",
pages = "1738--1742",
abstract = "We describe the VTeX Language Editing Dataset of Academic Texts (LEDAT), a dataset of text extracts from scientific papers that were edited by professional native English language editors at VTeX. The goal of the LEDAT is to provide a large data resource for the development of language evaluation and grammar error correction systems for the scientific community. We describe the data collection and the compilation process of the LEDAT. The new dataset can be used in many NLP studies and applications where deeper knowledge of the academic language and language editing is required. The dataset can be used also as a knowledge base of English academic language to support many writers of scientific papers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="daudaravicius-2014-language">
<titleInfo>
<title>Language Editing Dataset of Academic Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vidas</namePart>
<namePart type="family">Daudaravičius</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe the VTeX Language Editing Dataset of Academic Texts (LEDAT), a dataset of text extracts from scientific papers that were edited by professional native English language editors at VTeX. The goal of the LEDAT is to provide a large data resource for the development of language evaluation and grammar error correction systems for the scientific community. We describe the data collection and the compilation process of the LEDAT. The new dataset can be used in many NLP studies and applications where deeper knowledge of the academic language and language editing is required. The dataset can be used also as a knowledge base of English academic language to support many writers of scientific papers.</abstract>
<identifier type="citekey">daudaravicius-2014-language</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/714_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1738</start>
<end>1742</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Editing Dataset of Academic Texts
%A Daudaravičius, Vidas
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F daudaravicius-2014-language
%X We describe the VTeX Language Editing Dataset of Academic Texts (LEDAT), a dataset of text extracts from scientific papers that were edited by professional native English language editors at VTeX. The goal of the LEDAT is to provide a large data resource for the development of language evaluation and grammar error correction systems for the scientific community. We describe the data collection and the compilation process of the LEDAT. The new dataset can be used in many NLP studies and applications where deeper knowledge of the academic language and language editing is required. The dataset can be used also as a knowledge base of English academic language to support many writers of scientific papers.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/714_Paper.pdf
%P 1738-1742
Markdown (Informal)
[Language Editing Dataset of Academic Texts](http://www.lrec-conf.org/proceedings/lrec2014/pdf/714_Paper.pdf) (Daudaravičius, LREC 2014)
ACL
- Vidas Daudaravičius. 2014. Language Editing Dataset of Academic Texts. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1738–1742, Reykjavik, Iceland. European Language Resources Association (ELRA).