Here's the KUCut README:
### KU Wordcut Installation Instructions ###
### Copyright (C) 2004 Kasetsart University, NAiST Laboratory.
### Author: Sutee Sudprasert <su...@vivaldi.cpe.ku.ac.th>
Introduction
~~~~~~~~~~~~
KU wordcut is thai word segmentor that is difference from existing
segmentor such as CTTEX or SWATH.
The main objective of CTTEXT or SWATH is wrapping the text then speed
up of
computing is the most
important then accuracy or precision may be ommited. By the way, some
tasks
such as NLP, prefers
more precision than speed up of computing. In the mention before, we
will
attempt to build the segmentor
that is suitable for NLP tasks. Our segmentor can reduce some problem
that
be ommited in CTTEX or SWATH
such as unknown recognition and some case of boundary ambiguity.
Documentation
~~~~~~~~~~~~~
The algorithm using in this segmentor have been proposed in NCSEC 2003
processing (Thai word segmentation
based-on Local and Global Unsupervised Learning).
Requirement
~~~~~~~~~~~~~
python 2.5 or above
Installation
~~~~~~~~~~~~~
using the followed command on command line
python setup.py install
How to use
~~~~~~~~~~~~~
on command line use
kucut [option] <filename>
<filename> is input filename.
[option]
--line=?? for replace space with some special character,
default is "/n"
Report Bug & Comment
~~~~~~~~~~~~~~~~~~~~
E-mail : <su...@vivaldi.cpe.ku.ac.th> or <cpe11_su...@yahoo.com>
MSN : cpe11_su...@hotmail.com
ICQ : 88938507
--
View this message in context:
http://sword-dev.350566.n4.nabble.com/Observations-about-Thai-script-and-the-ThaiKJV-module-tp4333992p4335903.html
Sent from the SWORD Dev mailing list archive at Nabble.com.
_______________________________________________
sword-devel mailing list: sword-devel@crosswire.org
http://www.crosswire.org/mailman/listinfo/sword-devel
Instructions to unsubscribe/change your settings at above page
