explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-10 00:20:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Fix off-by-one in head reading

Browse Source
This commit is contained in:
Matthew Honnibal 2015-05-07 22:53:08 +02:00
parent 3d6b3fc6fb
commit 9568ebed08
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
spacy/syntax/conll.pyx
View File

@ -16,10 +16,11 @@ def read_json_file(loc):
labels = [] labels = []
iob_ents = [] iob_ents = []
for token in paragraph['tokens']: for token in paragraph['tokens']:
#print token['start'], token['orth'], token['head'], token['dep']
words.append(token['orth']) words.append(token['orth'])
ids.append(token['start']) ids.append(token['start'])
tags.append(token['tag']) tags.append(token['tag'])
heads.append(token['head'] if token['head'] >= 1 else token['start']) heads.append(token['head'] if token['head'] >= 0 else token['start'])
labels.append(token['dep']) labels.append(token['dep'])
iob_ents.append(token.get('iob_ent', 'O')) iob_ents.append(token.get('iob_ent', 'O'))