Moses (machine translation)

From Wikipedia, the free encyclopedia
Jump to: navigation, search
Moses
Development status stable
Written in C++, Perl
Operating system 32-bit MS Windows (NT/2000/XP), OS Portable, Linux, OS X
Platform cross-platform
Available in Multi-lingual
Type Machine translation
License LGPL (Free Software)
Website statmt.org/moses

Moses is a free software, statistical machine translation engine that allows automatically training translation models[clarify] 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. Its development is primarily supported by the EuroMatrix project, with funding by the European Commission.

Among its features are:

  • A beam search algorithm quickly finds the highest probability translation within a number of choices
  • Phrase-based, statistical machine translation of short text chunks
  • Handles words with factored representation (e.g., surface forms, lemma, part-of-speech, morphology, word classes)
  • Decodes confusion networks[clarify] to accommodate integration with ambiguous upstream tools, such as automatic speech recognizers
  • Factored translation models to enable the integration of linguistic and other information at various stages of the translation process
  • Support for large language models such as IRSTLM (an exact LM using memory-mapping) and RandLM (a randomised LM, based on Bloom Filters)

See also[edit]

References[edit]

  • 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.

External links[edit]