@conference{PROKOPIDIS16.778,
author = "Προκοπίδης, Προκόπης and Παπαβασιλείου, Βασίλης and Πιπερίδης, Στέλιος",
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.",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)",
editor = "Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Marko Grobelnik and Bente Maegaard and Joseph Mariani and Asuncion Moreno and Jan Odijk and Stelios Piperidis",
isbn = "978-2-9517408-9-1",
keywords = "parallel corpus, independent news stories, document pair detection",
month = "May",
publisher = "European Language Resources Association (ELRA)",
title = "{P}arallel {G}lobal {V}oices: a {C}ollection of {M}ultilingual {C}orpora with {C}itizen {M}edia {S}tories ",
url = "http://www.lrec-conf.org/proceedings/lrec2016/pdf/778_Paper.pdf",
year = "2016",
}