apertium(1)apertium(1)NAME
apertium - This application is part of ( apertium )
This tool is part of the apertium machine translation architecture: http://apertium.sf.net.
SYNOPSIS
apertium [-d datadir] [-f format] [-u] [-a] {language-pair} [infile [outfile]]
DESCRIPTION
apertium is the application that most people will be using as it simplifies the use of apertium/lt-toolbox tools for machine translation
purposes.
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:
o de-formatter: Separates the text to be translated from the format information.
o morphological-analyser: Tokenizes the text in surface forms.
o part-of-speech tagger: Chooses one surface forms among homographs.
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 corresponding transformations.
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 encapsula-
tion sequences used to protect certain characters in the source text.
OPTIONS -d datadir The directory holding the linguistic data. By default it will used the expected installation path.
language-pair The language pair: LANG1-LANG2 (for instance es-ca or ca-es).
-f format Specifies the format of the input and output files which can have these values:
o txt (default value) Input and output files are in text format.
o html Input and output files are in "html" format. This "html" is the one acceptd by the vast majority of web browsers.
o rtf Input and output files are in "rtf" format. The accepted "rtf" is the one generated by Microsoft WordPad (C) and Microsoft
Office (C) up to and including Office-97.
-u Disable marking of unknown words with the '*' character.
-a Enable marking of disambiguated words with the '=' character.
FILES
These are the two files that can be used with this command:
infile Input file (stdin by default).
outfile Output file (stdout by default).
SEE ALSO lt-proc(1), lt-comp(1), lt-expand(1), apertium-tagger(1).
BUGS
Lots of...lurking in the dark and waiting for you!
AUTHOR
(c) 2005,2006 Universitat d'Alacant / Universidad de Alicante. All rights reserved.
2006-03-08 apertium(1)
Check Out this Related Man Page
apertium-tagger(1)apertium-tagger(1)NAME
apertium-tagger - This application is part of ( apertium )
This tool is part of the apertium open-source machine translation architecture: http://www.apertium.org.
SYNOPSIS
apertium-tagger --train|-t {n} DIC CRP TSX PROB [--debug|-d]
apertium-tagger --supervised|-s {n} DIC CRP TSX PROB HTAG UNTAG [--debug|-d]
apertium-tagger --retrain|-r {n} CRP PROB [--debug|-d]
apertium-tagger --tagger|-g [--first|-f] PROB [--debug|-d] [INPUT [OUTPUT]]
DESCRIPTION
apertium-tagger is the application responsible for the apertium part-of-speech tagger training or tagging, depending on the calling
options. This command only reads from the standard input if the option --tagger or -g is used.
OPTIONS -t {n}, --train {n}
Initializes parameters through the Kupiec's method (unsupervised), then performs n iterations of the Baum-Welch training algorithm
(unsupervised).
-s {n}, --supervised {n}
Initializes parameters against a hand-tagged text (supervised) through the maximum likelihood estimate method, then performs n iter-
ations of the Baum-Welch training algorithm (unsupervised)
-r {n}, --retrain {n}
Retrains the model with n additional Baum-Welch iterations (unsupervised).
-g, --tagger
Tags input text by means of Viterbi algorithm.
-p, --show-superficial
Prints the superficial form of the word along side the lexical form in the output stream.
-f, --first
Used if conjuntion with -g (--tagger) makes the tagger to give all lexical forms of each word, being the choosen one in the first
place (after the lemma)
-d, --debug
Print error (if any) or debug messages while operating.
-m, --mark
Mark disambiguated words.
-h, --help
Display a help message.
FILES
These are the kinds of files used with each option:
DIC Full expanded dictionary file
CRP Training text corpus file
TSX Tagger specification file, in XML format
PROB Tagger data file, built in the training and used while tagging
HTAG Hand-tagged text corpus
UNTAG Untagged text corpus, morphological analysis of HTAG corpus to use both jointly with -s option
INPUT Input file, stdin by default
OUTPUT Output file, stdout by default
SEE ALSO lt-proc(1), lt-comp(1), lt-expand(1), apertium-translator(1), apertium(1).
BUGS
Lots of...lurking in the dark and waiting for you!
AUTHOR
Copyright (c) 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 Public License <http://www.gnu.org/licenses/gpl.html>.
2006-08-30 apertium-tagger(1)