@conference{BelEtAl-2012,
author = "Bel, Nuria and Παπαβασιλείου, Βασίλης and Προκοπίδης, Προκόπης and Toral, Antonio and Victoria Arranz and Arranz, Victoria",
abstract = "The objective of the PANACEA ICT-2007.2.2 EU project is to build a platform that automates the stages involved in the acquisition, production, updating and maintenance of the large language resources required by, among others, MT systems. The development of a Corpus Acquisition Component (CAC) for extracting monolingual and bilingual data from the web is one of the most innovative building blocks of PANACEA. The CAC, which is the first stage in the PANACEA pipeline for building Language Resources, adopts an efficient and distributed methodology to crawl for web documents with rich textual content in specific languages and predefined domains. The CAC includes modules that can acquire parallel data from sites with in-domain content available in more than one language. In order to extrinsically evaluate the CAC methodology, we have conducted several experiments that used crawled parallel corpora for the identification and extraction of parallel sentences using sentence alignment. The corpora were then successfully used for domain adaptation of Machine Translation Systems.",
address = "Istanbul, Turkey",
booktitle = "The Fifth Workshop on Building and Using Comparable Corpora",
title = "{M}ining and {E}xploiting {D}omain-Specific {C}orpora in the {P}ANACEA {P}latform ",
url = "http://www.lrec-conf.org/proceedings/lrec2012/workshops/16.BUCC2012%20Proceedings.pdf",
year = "2012",
}