From a4479f7122742b21e49f3be0f27083d300046161 Mon Sep 17 00:00:00 2001
From: Adam Radziszewski <adam.radziszewski@pwr.wroc.pl>
Date: Mon, 22 Oct 2012 11:51:33 +0200
Subject: [PATCH] update iobber_txt: default configs+models and possibility to
tag only, no chunk
---
iobber/iobber_txt.py | 25 +++++++++++++++----------
1 file changed, 15 insertions(+), 10 deletions(-)
diff --git a/iobber/iobber_txt.py b/iobber/iobber_txt.py
index 19346d8..bfb4f4e 100755
--- a/iobber/iobber_txt.py
+++ b/iobber/iobber_txt.py
@@ -64,17 +64,20 @@ def go():
parser.add_option('-O', '--output-file', type='string', action='store',
dest='out_path', default='',
help='set output filename (do not write to stdout)')
+ parser.add_option('--no-chunk', action='store_false',
+ dest='shall_chunk', default=True,
+ help='don\'t run the chunker, only the tagger')
parser.add_option('-c', '--chunker-config', type='string', action='store',
dest='chunker_config', default='kpwr.ini',
help='use given chunker config (default: kpwr.ini)')
parser.add_option('-C', '--chunker-model', type='string', action='store',
- dest='chunker_dir', default='',
+ dest='chunker_dir', default='model-kpwr04',
help='read chunker trained model from the given dir')
parser.add_option('-w', '--tagger-config', type='string', action='store',
dest='tagger_config', default='nkjp.ini',
help='use given tagger (wcrft) config (default: nkjp.ini)')
parser.add_option('-W', '--tagger-model', type='string', action='store',
- dest='tagger_dir', default='',
+ dest='tagger_dir', default='model_nkjp10_wcrft',
help='read tagger (wcrft) trained model from the given dir')
parser.add_option('-m', '--maca-config', type='string', action='store',
dest='maca_config', default='',
@@ -88,13 +91,13 @@ def go():
files = args
- chunkr = chunker.Chunker(options.chunker_config, options.chunker_dir)
tagr = tagger.Tagger(options.tagger_config, options.tagger_dir)
+ if options.shall_chunk:
+ chunkr = chunker.Chunker(options.chunker_config, options.chunker_dir)
if options.maca_config != '':
tagr.maca_config = options.maca_config
- # TODO option not to use chunker
# tag and chunk
inputs = []
outputs = []
@@ -114,11 +117,12 @@ def go():
outputs = [path + '.tag' for path in inputs]
if inputs:
tagr.load_model()
- chunkr.load_model()
- assert (tagr.tagset.name()
- == chunkr.tagset.name()), ('Tagger and chunker config must'
- + 'operate on the same tagset: %s v. %s' % (tagr.tagset.name(),
- chunkr.tagset.name()))
+ if options.shall_chunk:
+ chunkr.load_model()
+ assert (tagr.tagset.name()
+ == chunkr.tagset.name()), ('Tagger and chunker config must'
+ + 'operate on the same tagset: %s v. %s' % (tagr.tagset.name(),
+ chunkr.tagset.name()))
for in_path, out_path in zip(inputs, outputs):
if in_path and options.verbose:
sys.stderr.write('Processing %s...\n' % in_path)
@@ -142,7 +146,8 @@ def go():
new_sent = corpus2.AnnotatedSentence.cast_as_sentence(new_asent)
# preserve_ambiguity = False
tagr.disambiguate_sentence(new_sent)
- chunkr.tag_sentence(new_sent)
+ if options.shall_chunk:
+ chunkr.tag_sentence(new_sent)
# create a new paragraph with the new sentence
new_par.append(new_sent)
# save tagged paragraph
--
GitLab