@inproceedings{d46d98e11c3a400aa49ff50e7797881c,
title = "Billions of parallel words for free: Building and using the EU bookshop corpus",
abstract = "The European Union is a great source of high quality documents with translations into several languages. Parallel corpora from its publications are frequently used in various tasks, machine translation in particular. A source that has not systematically been explored yet is the EU Bookshop - an online service and archive of publications from various European institutions. The service contains a large body of publications in the 24 official of the EU. This paper describes our efforts in collecting those publications and converting them to a format that is useful for natural language processing in particular statistical machine translation. We report our procedure of crawling the website and various pre-processing steps that were necessary to clean up the data after the conversion from the original PDF files. Furthermore, we demonstrate the use of this dataset in training SMT models for English, French, German, Spanish, and Latvian.",
keywords = "Evaluation, Parallel corpus, Statistical machine translation",
author = "Raivis Skadiņ{\v s} and J{\"o}rg Tiedemann and Roberts Rozis and Daiga Deksne",
year = "2014",
language = "English",
series = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
publisher = "European Language Resources Association (ELRA)",
pages = "1850--1855",
editor = "Nicoletta Calzolari and Khalid Choukri and Sara Goggi and Thierry Declerck and Joseph Mariani and Bente Maegaard and Asuncion Moreno and Jan Odijk and Helene Mazo and Stelios Piperidis and Hrafn Loftsson",
booktitle = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
note = "9th International Conference on Language Resources and Evaluation, LREC 2014 ; Conference date: 26-05-2014 Through 31-05-2014",
}