@inproceedings{sauri-etal-2014-newsome,
title = "The {N}ew{S}o{M}e Corpus: A Unifying Opinion Annotation Framework across Genres and in Multiple Languages",
author = "Saur{\'\i}, Roser and
Domingo, Judith and
Badia, Toni",
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/350_Paper.pdf",
pages = "2229--2236",
abstract = "We present the NewSoMe (News and Social Media) Corpus, a set of subcorpora with annotations on opinion expressions across genres (news reports, blogs, product reviews and tweets) and covering multiple languages (English, Spanish, Catalan and Portuguese). NewSoMe is the result of an effort to increase the opinion corpus resources available in languages other than English, and to build a unifying annotation framework for analyzing opinion in different genres, including controlled text, such as news reports, as well as different types of user generated contents (UGC). Given the broad design of the resource, most of the annotation effort were carried out resorting to crowdsourcing platforms: Amazon Mechanical Turk and CrowdFlower. This created an excellent opportunity to research on the feasibility of crowdsourcing methods for annotating big amounts of text in different languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sauri-etal-2014-newsome">
<titleInfo>
<title>The NewSoMe Corpus: A Unifying Opinion Annotation Framework across Genres and in Multiple Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roser</namePart>
<namePart type="family">Saurí</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Judith</namePart>
<namePart type="family">Domingo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toni</namePart>
<namePart type="family">Badia</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 present the NewSoMe (News and Social Media) Corpus, a set of subcorpora with annotations on opinion expressions across genres (news reports, blogs, product reviews and tweets) and covering multiple languages (English, Spanish, Catalan and Portuguese). NewSoMe is the result of an effort to increase the opinion corpus resources available in languages other than English, and to build a unifying annotation framework for analyzing opinion in different genres, including controlled text, such as news reports, as well as different types of user generated contents (UGC). Given the broad design of the resource, most of the annotation effort were carried out resorting to crowdsourcing platforms: Amazon Mechanical Turk and CrowdFlower. This created an excellent opportunity to research on the feasibility of crowdsourcing methods for annotating big amounts of text in different languages.</abstract>
<identifier type="citekey">sauri-etal-2014-newsome</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/350_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2229</start>
<end>2236</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The NewSoMe Corpus: A Unifying Opinion Annotation Framework across Genres and in Multiple Languages
%A Saurí, Roser
%A Domingo, Judith
%A Badia, Toni
%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 sauri-etal-2014-newsome
%X We present the NewSoMe (News and Social Media) Corpus, a set of subcorpora with annotations on opinion expressions across genres (news reports, blogs, product reviews and tweets) and covering multiple languages (English, Spanish, Catalan and Portuguese). NewSoMe is the result of an effort to increase the opinion corpus resources available in languages other than English, and to build a unifying annotation framework for analyzing opinion in different genres, including controlled text, such as news reports, as well as different types of user generated contents (UGC). Given the broad design of the resource, most of the annotation effort were carried out resorting to crowdsourcing platforms: Amazon Mechanical Turk and CrowdFlower. This created an excellent opportunity to research on the feasibility of crowdsourcing methods for annotating big amounts of text in different languages.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/350_Paper.pdf
%P 2229-2236
Markdown (Informal)
[The NewSoMe Corpus: A Unifying Opinion Annotation Framework across Genres and in Multiple Languages](http://www.lrec-conf.org/proceedings/lrec2014/pdf/350_Paper.pdf) (Saurí et al., LREC 2014)
ACL