SFST
Revision as of 01:02, 24 May 2008 by Francis Tyers (talk | contribs) (New page: '''SFST''' (Stuttgart Finite State Toolkit) is a set of programs that can be used for writing morphological analysers. ==Downloading== A packaged version, with the <code>fst-proc</code> ...)
SFST (Stuttgart Finite State Toolkit) is a set of programs that can be used for writing morphological analysers.
Downloading
A packaged version, with the fst-proc
program for processing Apertium input streams can be downloaded from Apertium SVN:
$ svn co http://apertium.svn.sourceforge.net/svnroot/branches/sfst
- Compiling
Follow the standard steps:
$ sh autogen.sh $ ./configure $ make $ make install
Morphologies
The following
- Morph-IT! (Italian, 34,968 lemmas, LGPL)
- SMOR — comes in the SFST distribution (German, 1,096 lemmas, GPL)
Performance
The analysers produced are fast. For a 1.3Mb analyser (SMOR), it processes 1,100 words per second. Compare with lttoolbox which processes ~5,000 words per second.