explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-15 06:09:01 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix gold-preproc training mode

Browse Source
This commit is contained in:
Matthw Honnibal 2019-10-07 02:07:03 +02:00
parent 63ff233ba2
commit a132da1558
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/gold.pyx
View File

@ -252,8 +252,12 @@ class GoldCorpus(object):
raw_text = add_noise(raw_text, noise_level) raw_text = add_noise(raw_text, noise_level)
return [nlp.make_doc(raw_text)], paragraph_tuples return [nlp.make_doc(raw_text)], paragraph_tuples
else: else:
docs = []
raw_text, paragraph_tuples = make_orth_variants(nlp, None, paragraph_tuples, orth_variant_level=orth_variant_level) raw_text, paragraph_tuples = make_orth_variants(nlp, None, paragraph_tuples, orth_variant_level=orth_variant_level)
cats = paragraph_tuples.pop()
for i in range(len(paragraph_tuples)):
sent_tuples, brackets = paragraph_tuples[i]
sent_tuples = sent_tuples + [cats]
paragraph_tuples[i] = [sent_tuples, brackets]
return [Doc(nlp.vocab, words=add_noise(sent_tuples[1], noise_level)) return [Doc(nlp.vocab, words=add_noise(sent_tuples[1], noise_level))
for (sent_tuples, brackets) in paragraph_tuples], paragraph_tuples for (sent_tuples, brackets) in paragraph_tuples], paragraph_tuples