The different modules behind the apertium machine translation
architecture are in order:
o de-formatter: Separates the text to be translated from the
o morphological-analyser: Tokenizes the text in surface forms.
o part-of-speech tagger: Chooses one surface forms among
o lexical transfer module: Reads each source-language lexical
form and delivers a corresponding target-language lexical form.
o structural transfer module: Detects fixed-length patterns
of lexical forms (chunks or phrases) needing special processing due to
grammatical divergences between the two languages and performs the
o morphological generator: Delivers a target-language surface
form for each target-language lexical form, by suitably inflecting it.
o post-generator: Performs orthographical operations such as
contractions and apostrophations.
o re-formatter: Restores the format information encapsulated
by the de-formatter into the translated text and removes the
encapsulation sequences used to protect certain characters in the