omorfi-factorise − Factorise running Finnish text with omorfi for moses
omorfi-factorise.py [OPTION] [FILENAME...]
Factorises
running text using omorfi automata and hfst python library.
This script is mainly for moses pipelines between tokenise
and training.
−h, −−help
show this help message and exit
−f FSAPATH, −−fsa FSAPATH
Path to directory of HFST format automata
−i INFILE, −−input INFILE
source of analysis data
−v, −−verbose
print verbosely while processing
−o OUTFILE, −−output OUTFILE
print factors into OUTFILE
If no INFILE is given, input is read from standard input. If no OUTFILE is given, output is written to standard output.
The following command
omorfi-factorise.py −i rautatie.tokens −o rautatie.factors
factorises a tokenised corpus
Copyright
© 2015 Omorfi contributors Licence GPLv3: GNU GPL
version 3 <http://gnu.org/licenses/gpl.html>
This is free software: you are free to change and
redistribute it. There is NO WARRANTY, to the extent
permitted by law.