abbreviation(s): SMT

definition: Techniques for machine translation that combine a stochastic model of the target language with a stochastic relation between target and source language. Translation is seen as a decoding task similar to speech recognition. Both types of models can be build automatically from suitable training data.

related project(s):

• Statistical and Hybrid Machine Translation Between All European Languages (EuroMatrix)
• Centre for Next Generation Localisation
• ISI's Natural Language Group (ISI's NLG)

related organisation(s):

• University of Southern California (USC)
• University of Edinburgh
• Saarland University (UdS)
• Dublin City University (DCU)
• Language Weaver

related person(s):

• Martin Kay
• Daniel Marcu
• Andreas Eisele
• Hans Uszkoreit
• Marcello Federico
• Miles Osborne
• Chris Callison-Burch
• Hermann Ney
• Dekai Wu
• Franz Josef Och
• Frederick Jelínek
• Kevin Knight
• Jan Hajic
• Philipp Koehn

related system(s) / resource(s):

• Moses
• Systran Information and Translation Technologies
• Pharaoh
• Lucy
• Language Weaver Statistical Machine Translation products
• PLAINtranslate

relevant source(s):

• Syntax for Statistical Machine Translation
• Ongoing Research in Machine Translation
• Technical Papers & Resources

related publication(s):

A Statistical Approach to Machine Translation.
Peter F. Brown and John Cocke and Stephen Della Pietra and Vincent J. Della Pietra and Fredrick Jelinek and John D. Lafferty and Robert L. Mercer and Paul S. Roossin.
Computational Linguistics. 16 (2). 1990. 79-85.
http://www.ilc.cnr.it/EAGLES96/layout/layout.html

The mathematics of statistical machine translation: Parameter estimation.
Peter F. Brown and Vincent J. Della Pietra and Stephen Della Pietra and Robert L. Mercer.
Computational Linguistics. 19 (2). 1993.

Statistical Methods for Machine Translation.
Verbmobil: Foundations of Speech-to-Speech Translation.
Stephan Vogel and Franz Josef Och and Christoph Tillmann and Sonja Nießen and Hassan Sawaf and Hermann Ney, Wolfgang Wahlster.
2000. 377-393.

Fast Decoding and Optimal Decoding for Machine Translation.
Germann, Ulrich and Jahr, Michael and Knight, Kevin and Marcu, Daniel and Yamada, Kenji.
Proceedings of 39th Annual Meeting of the Association for Computational Linguistics. 2001. 228--235.

A Syntax-based Statistical Translation Model.
Yamada, Kenji and Knight, Kevin.
Proceedings of 39th Annual Meeting of the Association for Computational Linguistics. 2001. 523--530.

Multi-Engine Machine Translation with an Open-Source (SMT) Decoder.
Yu Chen and Andreas Eisele and Christian Federmann and Eva Hasler and Michael Jellinghaus and Silke Theison
Proceedings of 39th Annual Meeting of the Association for Computational Linguistics. ACL 2007: proceedings of the Second Workshop on Statistical Machine Translation, June 23, 2007, Prague, Czech Republic. pp. 193-196.

Moses: Open Source Toolkit for Statistical Machine Translation.
Philipp Koehn and Hieu Hoang and Alexandra Birch and Chris Callison-Burch and Marcello Federico and Nicola Bertoldi and Brooke Cowan and Wade Shen and Christine Moran and Richard Zens and Chris Dyer and Ondrej Bojar and Alexandra Constantin and Evan Herbst
Proceedings of ACL 2007, demonstration session.

http://www.statmt.org/wmt08/

http://ece.engr.uno.edu/ssst/