@inproceedings{sabou-etal-2014-corpus,
title = "Corpus Annotation through Crowdsourcing: Towards Best Practice Guidelines",
author = "Sabou, Marta and
Bontcheva, Kalina and
Derczynski, Leon and
Scharl, Arno",
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/497_Paper.pdf",
pages = "859--866",
abstract = "Crowdsourcing is an emerging collaborative approach that can be used for the acquisition of annotated corpora and a wide range of other linguistic resources. Although the use of this approach is intensifying in all its key genres (paid-for crowdsourcing, games with a purpose, volunteering-based approaches), the community still lacks a set of best-practice guidelines similar to the annotation best practices for traditional, expert-based corpus acquisition. In this paper we focus on the use of crowdsourcing methods for corpus acquisition and propose a set of best practice guidelines based in our own experiences in this area and an overview of related literature. We also introduce GATE Crowd, a plugin of the GATE platform that relies on these guidelines and offers tool support for using crowdsourcing in a more principled and efficient manner.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sabou-etal-2014-corpus">
<titleInfo>
<title>Corpus Annotation through Crowdsourcing: Towards Best Practice Guidelines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Sabou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalina</namePart>
<namePart type="family">Bontcheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Derczynski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arno</namePart>
<namePart type="family">Scharl</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>Crowdsourcing is an emerging collaborative approach that can be used for the acquisition of annotated corpora and a wide range of other linguistic resources. Although the use of this approach is intensifying in all its key genres (paid-for crowdsourcing, games with a purpose, volunteering-based approaches), the community still lacks a set of best-practice guidelines similar to the annotation best practices for traditional, expert-based corpus acquisition. In this paper we focus on the use of crowdsourcing methods for corpus acquisition and propose a set of best practice guidelines based in our own experiences in this area and an overview of related literature. We also introduce GATE Crowd, a plugin of the GATE platform that relies on these guidelines and offers tool support for using crowdsourcing in a more principled and efficient manner.</abstract>
<identifier type="citekey">sabou-etal-2014-corpus</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/497_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>859</start>
<end>866</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpus Annotation through Crowdsourcing: Towards Best Practice Guidelines
%A Sabou, Marta
%A Bontcheva, Kalina
%A Derczynski, Leon
%A Scharl, Arno
%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 sabou-etal-2014-corpus
%X Crowdsourcing is an emerging collaborative approach that can be used for the acquisition of annotated corpora and a wide range of other linguistic resources. Although the use of this approach is intensifying in all its key genres (paid-for crowdsourcing, games with a purpose, volunteering-based approaches), the community still lacks a set of best-practice guidelines similar to the annotation best practices for traditional, expert-based corpus acquisition. In this paper we focus on the use of crowdsourcing methods for corpus acquisition and propose a set of best practice guidelines based in our own experiences in this area and an overview of related literature. We also introduce GATE Crowd, a plugin of the GATE platform that relies on these guidelines and offers tool support for using crowdsourcing in a more principled and efficient manner.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/497_Paper.pdf
%P 859-866
Markdown (Informal)
[Corpus Annotation through Crowdsourcing: Towards Best Practice Guidelines](http://www.lrec-conf.org/proceedings/lrec2014/pdf/497_Paper.pdf) (Sabou et al., LREC 2014)
ACL