machine translation application platform
apertium is the application that most people will be
using as it simplifies the use of apertium/lt-toolbox tools for machine
This tool tries to ease the use of lt-toolbox
(which contains all the lexical processing modules and tools) and
apertium (which contains the rest of the engine) by
providing a unique front-end to the end-user.
The different modules behind the apertium machine translation
architecture are in order:
- Separates the text to be translated from the format information.
- Tokenizes the text in surface forms.
- part-of-speech tagger
- Chooses one surface forms among homographs.
- lexical transfer module
- Reads each source-language lexical form and delivers a corresponding
target-language lexical form.
- 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 corresponding transformations.
- morphological generator
- Delivers a target-language surface form for each target-language lexical
form, by suitably inflecting it.
- Performs orthographical operations such as contractions and
- 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 source text.
These are the two files that can be used with this command:
- The directory holding the linguistic data. By default it will use the
expected installation path.
- The language pair:
instance “es-ca” or “ca-es”).
- Specifies the format of the input and output files which can have these
- (default value) Input and output files are in text
- Input and output files are in “html” format. This
“html” is the one accepted by the vast majority of web
- Input and output files are in “html” format, but
preserving native encoding characters rather than using HTML text
- Input and output files are in “rtf” format. The accepted
“rtf” is the one generated by Microsoft WordPad and
Microsoft Office up to and including Office 97.
- Disable marking of unknown words with the
- Enable header-detection (only used in some language pairs; will lead to
❡’ characters in pairs
that don't support it).
- Enable marking of disambiguated words with the
Copyright © 2005, 2006 Universitat d'Alacant / Universidad de Alicante.
This is free software. You may redistribute copies of it under the terms of
the GNU General
Many... lurking in the dark and waiting for you!
- use a translation memory to recycle translations
- translation direction using the translation memory, by default
“direction” is used instead
- lists the available translation directions and exits direction typically,
LANG1–LANG2, but see
modes.xml in language data
- Input file (
- Output file (