sourCEntral - mobile manpages

pdf

mbma

NAME

mbma - (Dutch) morphological analyzer

SYNOPSIS

mbma -t test-file

DESCRIPTION

mbma will tokenize, tag, and morphologically segment word tokens in Dutch text files. The default is to use the
Frog config file.

OPTIONS

-c <configfile>

set the configuration using ’file’

-d <level>

set debug level.

--notagger

Don’t use a tagger to disambiguate. All variants are shown. The default is to use the Dutch CGN tagger.

--notokenizer

Don’t use a tokenizer. Assume al input to be tokenized. The default is to use the Ucto Tokenizer for Dutch.

-h

give some help

-t <file>

process ’file’

BUGS

likely

AUTHORS

Ko van der Sloot Timbl AT uvt DOT nl

Antal van den Bosch Timbl AT uvt DOT nl

SEE ALSO

frog(1) ucto(1) mblem(1)

pdf