explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 02:06:31 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Ignore adjective supersenses

Browse Source
This commit is contained in:
Matthew Honnibal 2015-07-03 04:46:11 +02:00
parent dbcef2b76e
commit c60cc22390
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
bin/init_model.py
View File

@ -87,6 +87,8 @@ def _read_senses(loc):
word = sense_strings.pop(0) word = sense_strings.pop(0)
for sense in sense_strings: for sense in sense_strings:
pos, sense = sense[3:].split('.') pos, sense = sense[3:].split('.')
if pos[0].upper() == 'A':
continue
sense_name = '%s_%s' % (pos[0].upper(), sense.lower()) sense_name = '%s_%s' % (pos[0].upper(), sense.lower())
if sense_name != 'N_tops': if sense_name != 'N_tops':
sense_id = sense_names[sense_name] sense_id = sense_names[sense_name]
@ -124,10 +126,6 @@ def setup_vocab(src_dir, dst_dir):
for lemma in lemmatizer(word.lower(), pos): for lemma in lemmatizer(word.lower(), pos):
lemmas.append(lemma) lemmas.append(lemma)
orth_senses.update(senses[lemma][pos]) orth_senses.update(senses[lemma][pos])
if word.lower() == 'dogging':
print word
print lemmas
print [spacy.senses.STRINGS[si] for si in orth_senses]
entry['senses'] = list(sorted(orth_senses)) entry['senses'] = list(sorted(orth_senses))
vocab[word] = entry vocab[word] = entry
vocab.dump(str(dst_dir / 'lexemes.bin')) vocab.dump(str(dst_dir / 'lexemes.bin'))