Welcome to Moses!

Moses is a statistical machine translation system that allows you to automatically train translation models for any language pair. All you need is a collection of translated texts (parallel corpus).

• beam-search: an efficient search algorithm finds quickly the highest probability translation among the exponential number of choices
• phrase-based: the state-of-the-art in statistical machine translation allows the translation of short text chunks
• factored: words may have factored representation (surface forms, lemma, part-of-speech, morphology, word classes...)

Features

• Moses is a drop-in replacement for Pharaoh, the popular phrase-based decoder, with many extensions.
• Moses allows the decoding of confusion networks, enabling easy integration with ambiguous upstream tools, such as automatic speech recognizers
• Moses features novel factored translation models, which enable the integration linguistic and other information at many stages of the translation process

Get started

The released software includes a command line executable which can used for decoding. The source code for the decoder, as well as binaries for Windows and Linux, can be downloaded from Sourceforge. Download the latest binary release. However, if you want the addition scripts to create factored phrase tables and train the weights of the models, please download the complete snapshot via SVN. This repository also contains regression tests, should you be interested in enhancing the decoder.

Learn about the decoder, training models, and tuning. Follow the step-by-step guide. The documentation available at this web side is also compiled in a printable manual.

Acknowledgement

The development of Moses is mainly supported under the EuroMatrix project, P6-IST-5-034291-STP, funded by the European Commission under Framework Programme 6, and received additional support from

• University of Edinburgh, Scotland
• RWTH Aachen, Germany
• ITC-irst, Trento, Italy
• University of Maryland, College Park, United States
• Massachusetts Institute of Technology, United States
• Charles University, Prague, Czech Republic
• US funding agencies DARPA, NSF, and Department of Defence
• EU funding through the TC-Star project

Open Source License

Moses is licensed under the LGPL.