diff options
Diffstat (limited to 'scripts/analysis/smtgui/README')
| -rw-r--r-- | scripts/analysis/smtgui/README | 11 |
1 files changed, 11 insertions, 0 deletions
diff --git a/scripts/analysis/smtgui/README b/scripts/analysis/smtgui/README index c86cd9c1a..e6bcabb2e 100644 --- a/scripts/analysis/smtgui/README +++ b/scripts/analysis/smtgui/README @@ -29,3 +29,14 @@ $ $DATA/test/combine-features.perl CORPUS lc+pos lemma > CORPUS.lc+pos+lemma $ rm CORPUS.pos-tmp (cleanup) where $BIN=/export/ws06osmt/bin, $DATA=/export/ws06osmt/data. + +To get German POS tags and lemmas from a words-only corpus (the first step must be run on linux): + +$ $BIN/recase.perl --in CORPUS.lc --model $MODELS/en-de/recaser/pharaoh.ini > CORPUS.recased (call pharaoh with a lowercase->uppercase model) +$ $BIN/run-lopar-tagger-lowercase.perl CORPUS.recased CORPUS.recased.lopar (call LOPAR) +$ $DATA/test/factor-stem.de.perl < CORPUS.recased.lopar > CORPUS.stem +$ $BIN/lowercase.latin1.perl < CORPUS.stem > CORPUS.lcstem (as you might guess, assumes latin-1 encoding) +$ $DATA/test/factor-pos.de.perl < CORPUS.recased.lopar > CORPUS.pos +$ $DATA/test/combine-features.perl CORPUS lc pos lcstem > CORPUS.lc+pos+lcstem + +where $MODELS=/export/ws06osmt/models. |