explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-05 01:34:14 +03:00
Code Issues Packages Projects Releases Wiki Activity

Set gold.sent_starts in ud_train

Browse Source
This commit is contained in:
Matthew Honnibal 2018-05-07 15:52:47 +02:00
parent bf19f22340
commit eddc0e0c74
1 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
spacy/cli/ud_train.py
View File

@ -124,13 +124,16 @@ def read_conllu(file_):
return docs
def _make_gold(nlp, text, sent_annots):
def _make_gold(nlp, text, sent_annots, drop_deps=0.0):
# Flatten the conll annotations, and adjust the head indices
flat = defaultdict(list)
sent_starts = []
for sent in sent_annots:
flat['heads'].extend(len(flat['words'])+head for head in sent['heads'])
for field in ['words', 'tags', 'deps', 'entities', 'spaces']:
flat[field].extend(sent[field])
sent_starts.append(True)
sent_starts.extend([False] * (len(sent['words'])-1))
# Construct text if necessary
assert len(flat['words']) == len(flat['spaces'])
if text is None:
@ -138,6 +141,12 @@ def _make_gold(nlp, text, sent_annots):
doc = nlp.make_doc(text)
flat.pop('spaces')
gold = GoldParse(doc, **flat)
gold.sent_starts = sent_starts
for i in range(len(gold.heads)):
if random.random() < drop_deps:
gold.heads[i] = None
gold.labels[i] = None
return doc, gold
#############################