Memory based tagger
mbt [options]
mbt is a memory-based tagger that can tag sequences, based on training files generated by mbtg.
-h or --help
show help
-s settingsfile
use a settingsfile as generated by mbtg
Or:
-l <lexiconfile>
-r <ambitagfile>
-k <known words case base>
-u <unknown words case base>
-D <loglevel>
Possible options levels are LogNormal , LogDebug , LogHeavy and LogExtreme
-e <sentence delimiter> (default '<utt>')
-E <enriched tagged testfile>
-t <testfile>
-T <tagged testfile> (default is untagged stdin)
-o <outputfile> (default stdout)
-Otimbl options
(Note: there is NO SPACE between O and the options)
<options> classifier options for both known and unknown words instance bases K: <options> classifier options for known words instance base U: <options> classifier options for unknown words instance base valid
timbl options are: a d k m q v w x -
-B <beamsize for search> (default = 1)
-v di
add distance to output
-v db
add distribution to output
-v c
add confidence to output
-V or --version
show version info.
-L <file with list of frequent words>
possibly
Ko van der Sloot [email protected]
Antal van den Bosch [email protected]