@inproceedings{L16-1144,
 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.
},
 address = {Portorož, Slovenia},
 author = {Prokopis Prokopidis and Vassilis Papavassiliou and Stelios Piperidis},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {900--905},
 publisher = {European Language Resources Association (ELRA)},
 title = {Parallel Global Voices: a Collection of Multilingual Corpora with Citizen Media Stories},
 url = {https://www.aclweb.org/anthology/L16-1144},
 year = {2016}
}