Machine Translation/Statistics
Statistical machine translation
editLanguage models
editLanguage models are used in MT for a) scoring arbitrary sequences of words (tokens) and b) given a sequence of tokens, they predict what token will likely to follow the sequence. Formally, language models are probability distributions over sequences of tokens in a given language.
N-gram models
editCharacter-based models
editRecently, it was shown that it is possible to use sub-words, characters or even bytes as basic units for language modelling[citation needed]. There are a few events focused particularly on such models and in general, processing language data on sub-word units, e.g. SCLem 2017.
Translation models
editIBM models 1-5
editPhrase-based models
editFactored translation models
editSyntax- and tree-based models
editSynchronous phrase grammar
editParallel tree-banks
editSyntactic rules extraction
editDecoding
editBeam search
edit| This section is a stub. You can help Wikibooks by expanding it. |