Moses (machine translation)
|Written in||C++, Perl|
|Operating system||32-bit MS Windows (NT/2000/XP), OS Portable, Linux, OS X|
|License||GNU Library or Lesser General Public License (LGPL)|
Moses is a free software statistical machine translation engine that allows automatically training translation models for any language pair given a collection of source and target text pairs (parallel corpus). It is released under the LGPL licence and available both as source code and binaries for Windows and Linux.
Amongst its features are:
- beam-search: an efficient search algorithm that quickly finds 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...)
- decoding of confusion networks, enabling easy integration with ambiguous upstream tools, such as automatic speech recognizers
- novel factored translation models, which enable the integration of linguistic and other information at many stages of the translation process
- support for large language models: Moses can use either IRSTLM (an exact LM using memory-mapping) or else RandLM (a randomised LM, based on Bloom Filters)
Moses development is, amongst other international organisations, mainly supported by EuroMatrix project and funded by the European Commission.
- 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. (2007) "Moses: Open Source Toolkit for Statistical Machine Translation". Annual Meeting of the Association for Computational Linguistics (ACL), demonstration session, Prague, Czech Republic, June 2007.