#!/bin/sh

# Set these paths appropriately

BIN=/mnt/minerva1/nlp/software/TreeTagger/bin
CMD=/mnt/minerva1/nlp/software/TreeTagger/cmd
LIB=/mnt/minerva1/nlp/software/TreeTagger/lib

OPTIONS="-token -lemma -sgml -pt-with-lemma"

TOKENIZER=${CMD}/tokenize.pl
TAGGER=${BIN}/tree-tagger
ABBR_LIST=${LIB}/english-abbreviations
PARFILE=${LIB}/english.par
LEXFILE=${LIB}/english-lexicon.txt

$TOKENIZER -e -a $ABBR_LIST $* |
# remove empty lines
grep -v '^$' |
# external lexicon lookup
perl $CMD/lookup.perl $LEXFILE |
# tagging
$TAGGER $OPTIONS $PARFILE













#!/bin/sh

# In order to activate external lexicon lookup
# you have to uncomment the respective line below
# i.e. remove the hash symbol in front of it.
# The external lexicon must be stored in a file named
# "german-lexicon.txt" in the subdirectory "lib".
# See the Perl script "lookup.perl" for more information
# on the format of this file.

# Set these paths appropriately

BIN=/mnt/minerva1/nlp/software/TreeTagger/bin
CMD=/mnt/minerva1/nlp/software/TreeTagger/cmd
LIB=/mnt/minerva1/nlp/software/TreeTagger/lib

OPTIONS="-token -lemma -sgml -pt-with-lemma"

TOKENIZER=${CMD}/tokenize.pl
TAGGER=${BIN}/tree-tagger
ABBR_LIST=${LIB}/german-abbreviations
PARFILE=${LIB}/german.par
LEXFILE=${LIB}/german-lexicon.txt
FILTER=${CMD}/filter-german-tags

$TOKENIZER -a $ABBR_LIST $* |
# external lexicon lookup
perl $CMD/lookup.perl $LEXFILE |
# tagging
$TAGGER $OPTIONS $PARFILE  |
# error correction
$FILTER