MEDAR Evaluation Package ======================== The material provided in the MEDAR Evaluation Package is protected by Copyright laws and international copyright treaties as well as other intellectual property laws and treaties provisions. Any copy, except for backup purposes, on any media whatsoever is strictly prohibited and shall constitute a copyright infringement. ELDA - Evaluation and Language resources Distribution Agency 55-57 Rue Brillat-Savarin 75013 Paris tel : +33 1 43 13 33 33 fax : +33 1 43 13 33 30 courriel : contact@elda.org Copyright owners : - MEDAR consortium - ELDA - Islam Online (http://www.islamonline.net) - Meedan (http://www.meedan.net) - United Nations Corpora (http://www.uncorpora.org) - Wikipedia (http://ar.wikipedia.org) - Wikibooks (http://ar.wikibooks.org) - Wikinews (http://ar.wikinews.org) - Wikiquote (http://fr.wikiquote.org) - Wikisource (http://ar.wikisource.org) - MOSES is licensed under the LGPL. The use is granted the right to use it as is. The user agrees to share any changes to the code with the community. - GIZA++ (training of statistical translation models, http://fjoch.com/GIZA++.html) is distributed under the GNU Public License (GPL). - SRILM is a toolkit for building and applying statistical language models, primarily for use in speech recognition, statistical tagging and segmentation, and machine translation. It has been under development in the SRI Speech Technology and Research Laboratory since 1995. The toolkit has also greatly benefited from its use and enhancements during the Johns Hopkins University/CLSP summer workshops in 1995, 1996, 1997, and 2002. SRILM is included herein free of charge under an “open source community license”, meaning that user can use it freely for non-profit purposes, and user agrees to share  any changes you make with the rest of the user community. - IRSTLM Toolkit: The IRST Language Modeling Toolkit features algorithms and data structures suitable to estimate, store, and access very large language models. The toolkit has been integrated into a popular open source Statistical Machine Translation decoder called Moses, and is compatible with language models created with other tools, such as the SRILM Toolkit. IRSTLM is licensed under the LGPL. - Champollion Tool Kit (CTK) is distributed by the Linguistic Data Consortium (LDC) under the GNU Public License (GPL). - Hunalign is licensed under the GNU LGPL version 2.1 or later. The following acknowledgement is required: - MEDAR 2010 Evaluation Package, distributed by ELRA on behalf of the MEDAR Consortium. - Moses: Philipp Koehn, Hieu Hoang, Alexandra Birch, Chris Callison-Burch, Marcello Federico, Nicola Bertoldi, Brooke Cowan, Wade Shen, Christine Moran, Richard Zens, Chris Dyer, Ondrej Bojar, Alexandra Constantin, Evan Herbst, “Moses: Open Source Toolkit for Statistical Machine Translation”, Annual Meeting of the Association for Computational Linguistics (ACL), demonstration session, Prague, Czech Republic, June 2007. - Giza++: Franz Josef Och, Hermann Ney. “A Systematic Comparison of Various Statistical Alignment Models”, Computational Linguistics, volume 29, number 1, pp. 19-51 March 2003. - SRILM: A. Stolcke, “SRILM - An Extensible Language Modeling Toolkit”, in Proceeding of Intl. Conf. Spoken Language Processing, Denver, Colorado, September 2002. - IRSTLM:  M. Federico, N. Bertoldi, M. Cettolo, “IRSTLM: an Open Source Toolkit for Handling Large Scale Language Models”, in Proceedings of Interspeech, Brisbane, Australia, 2008. - Champollion Tool Kit (CTK), Xiaoyi Ma, Champollion: A Robust Parallel Text Sentence Aligner, in Proceedings of LREC 2006: Fifth International Conference on Language Resources and Evaluation, Genova, Italy, 2006. - Hunalign, D. Varga, L. Németh, P. Halácsy, A. Kornai, V. Trón, V. Nagy (2005), Parallel corpora for medium density languages, in Proceedings of the RANLP 2005, pages 590-596.