Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

* Uncomment NER training

This commit is contained in:
Matthew Honnibal 2015-06-16 23:36:54 +02:00
parent 9b13d11ab3
commit 4dad4058c3
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
bin/parser/train.py
View File

@ -133,7 +133,7 @@ def train(Language, gold_tuples, model_dir, n_iter=15, feat_set=u'basic',
gold = GoldParse(tokens, annot_tuples, make_projective=True) gold = GoldParse(tokens, annot_tuples, make_projective=True)
loss += nlp.parser.train(tokens, gold) loss += nlp.parser.train(tokens, gold)
#nlp.entity.train(tokens, gold) nlp.entity.train(tokens, gold)
nlp.tagger.train(tokens, gold.tags) nlp.tagger.train(tokens, gold.tags)
random.shuffle(gold_tuples) random.shuffle(gold_tuples)
print '%d:\t%d\t%.3f\t%.3f\t%.3f\t%.3f' % (itn, loss, scorer.uas, scorer.ents_f, print '%d:\t%d\t%.3f\t%.3f\t%.3f\t%.3f' % (itn, loss, scorer.uas, scorer.ents_f,
@ -160,7 +160,7 @@ def evaluate(Language, gold_tuples, model_dir, gold_preproc=False, verbose=False
if raw_text is None: if raw_text is None:
tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1]) tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1])
nlp.tagger(tokens) nlp.tagger(tokens)
#nlp.entity(tokens) nlp.entity(tokens)
nlp.parser(tokens) nlp.parser(tokens)
else: else:
tokens = nlp(raw_text, merge_mwes=False) tokens = nlp(raw_text, merge_mwes=False)
@ -182,7 +182,7 @@ def write_parses(Language, dev_loc, model_dir, out_loc, beam_width=None):
if raw_text is None: if raw_text is None:
tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1]) tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1])
nlp.tagger(tokens) nlp.tagger(tokens)
#nlp.entity(tokens) nlp.entity(tokens)
nlp.parser(tokens) nlp.parser(tokens)
else: else:
tokens = nlp(raw_text, merge_mwes=False) tokens = nlp(raw_text, merge_mwes=False)