Abstract
Statistical machine translation is often criticized for slow decoding time. We address this issue by presenting a new tool for enabling Moses, a state of the art machine translation system, to be run on gLite based Grid infrastructures. It implements a workflow model for equally distributing the decoding task among several worker nodes in a cluster. We report experimental results for possible speed-ups and envision how natural language processing scientists can benefit from existing Grid infrastructures for solving processing, storage and collaboration issues.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Koehn, P., Hoang, H., Birch, A., Callison-Burch, C., Federico, M., Bertoldi, N., Cowan, B., Shen, W., Moran, C., Zens, R., Dyer, C., Bojar, O., Constantin, A., Herbst, E.: Moses: Open Source Toolkit for Statistical Machine Translation. In: Annual Meeting of the Association for Computational Linguistics (ACL), demonstration session, Prague, Czech Republic (2007)
SEE-GRID eInfrastructure for regional eScience, http://www.see-grid-sci.eu/
Haddow, B.: Adding Multi-Threaded Decoding to Moses. In: The Prague Bulletin of Mathematical Linguistics, Prague, Czech Republic, pp. 57–66 (2010)
Stolić, M., Zdravkova, K.: Resources for machine translation of the Macedonian language. In: 1st International Conference ICT Innovations, Ohrid, Macedonia (2009)
Tyers, F., Alperen, M.: South-East European Times: A parallel corpus of the Balkan languages. In: Proceedings of the Workshop on Exploitation of multilingual resources and tools for Central and (South) Eastern European Languages LREC (2010)
Federico, M., Bertoldi, N., Cettolo, M.: IRSTLM: an Open Source Toolkit for Handling Large Scale Language Models. In: Proceedings of the Interspeech, Brisbane, Australia (2008)
EGI European Grid Initiative, http://www.egi.eu/
Misev, A., Atanassov, E.: ULMon - Grid Monitoring from User Point of View. In: Proceeding of the 31st International Conference on Information Technology Interfaces ITI 2009, Cavtat/Dubrovnik, Croatia, pp. 621–626 (2009)
Laure, E., Hemmer, F., Prelz, F., Beco, S., Fisher, S., Livny, M., Guy, L., Barroso, M., Buncic, P., Kunszt, P.: Middleware for the next generation grid infrastructure. In: Proceedings of CHEP, Interlaken, Switzerland (2004)
Pacini, F.: JDL attributes specification. Technical report, EGEE Document EGEE-JRA1-TEC-590869-JDL-Attributes-v0-9 (2007)
EGEE: Enabling grids for E-sciencE, http://www.eu-egee.org/
LHC Computing Grid, http://lcg.web.cern.ch/LCG/
Santos, N., Koblitz, B.: Metadata services on the grid. In: Proceedings of Advanced Computing and Analysis Techniques ACAT, Berlin, Germany (2005)
Giménez, J., Màrquez, L.: SVMTool: A general POS tagger generator based on Support Vector Machines. In: Proceedings of the Fourth International Conference on Language Resources and Evaluation, Lisbon, Portugal (2004)
Koehn, P.: Europarl: A Parallel Corpus for Statistical Machine Translation. In: Machine Translation Summit X, Phuket, Thailand, pp. 79–86 (2005)
Erjavec, T.: MULTEXT-East Version 4: Multilingual Morphosyntactic Specifications, Lexicons and Corpora. In: The Seventh International Conference on Language Resources and Evaluation, LREC 2010, Malta (2010)
Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: A method for automatic evaluation of machine translation. In: 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, USA, pp. 311–318 (2002)
Oracle Grid Engine, http://www.oracle.com/us/products/tools/oracle-grid-engine-075549.html
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Stolić, M., Mišev, A. (2011). Parallel Machine Translation for gLite Based Grid Infrastructures. In: Gusev, M., Mitrevski, P. (eds) ICT Innovations 2010. ICT Innovations 2010. Communications in Computer and Information Science, vol 83. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19325-5_14
Download citation
DOI: https://doi.org/10.1007/978-3-642-19325-5_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19324-8
Online ISBN: 978-3-642-19325-5
eBook Packages: Computer ScienceComputer Science (R0)