@inproceedings{prokopidis-etal-2016-parallel,
title = "Parallel {G}lobal {V}oices: a Collection of Multilingual Corpora with Citizen Media Stories",
author = "Prokopidis, Prokopis and
Papavassiliou, Vassilis and
Piperidis, Stelios",
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/L16-1144",
pages = "900--905",
abstract = "We present a new collection of multilingual corpora automatically created from the content available in the Global Voices websites, where volunteers have been posting and translating citizen media stories since 2004. We describe how we crawled and processed this content to generate parallel resources comprising 302.6K document pairs and 8.36M segment alignments in 756 language pairs. For some language pairs, the segment alignments in this resource are the first open examples of their kind. In an initial use of this resource, we discuss how a set of document pair detection algorithms performs on the Greek-English corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="prokopidis-etal-2016-parallel">
<titleInfo>
<title>Parallel Global Voices: a Collection of Multilingual Corpora with Citizen Media Stories</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prokopis</namePart>
<namePart type="family">Prokopidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vassilis</namePart>
<namePart type="family">Papavassiliou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</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>We present a new collection of multilingual corpora automatically created from the content available in the Global Voices websites, where volunteers have been posting and translating citizen media stories since 2004. We describe how we crawled and processed this content to generate parallel resources comprising 302.6K document pairs and 8.36M segment alignments in 756 language pairs. For some language pairs, the segment alignments in this resource are the first open examples of their kind. In an initial use of this resource, we discuss how a set of document pair detection algorithms performs on the Greek-English corpus.</abstract>
<identifier type="citekey">prokopidis-etal-2016-parallel</identifier>
<location>
<url>https://aclanthology.org/L16-1144</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>900</start>
<end>905</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parallel Global Voices: a Collection of Multilingual Corpora with Citizen Media Stories
%A Prokopidis, Prokopis
%A Papavassiliou, Vassilis
%A Piperidis, Stelios
%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 prokopidis-etal-2016-parallel
%X We present a new collection of multilingual corpora automatically created from the content available in the Global Voices websites, where volunteers have been posting and translating citizen media stories since 2004. We describe how we crawled and processed this content to generate parallel resources comprising 302.6K document pairs and 8.36M segment alignments in 756 language pairs. For some language pairs, the segment alignments in this resource are the first open examples of their kind. In an initial use of this resource, we discuss how a set of document pair detection algorithms performs on the Greek-English corpus.
%U https://aclanthology.org/L16-1144
%P 900-905
Markdown (Informal)
[Parallel Global Voices: a Collection of Multilingual Corpora with Citizen Media Stories](https://aclanthology.org/L16-1144) (Prokopidis et al., LREC 2016)
ACL