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

don't require json-files to have syntactic annotation

This commit is contained in:
Wolfgang Seeker 2016-04-22 16:32:27 +02:00
parent 12024b0b0a
commit 4d7f393fae
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/gold.pyx
View File

@ -151,9 +151,9 @@ def read_json_file(loc, docs_filter=None):
for i, token in enumerate(sent['tokens']): for i, token in enumerate(sent['tokens']):
words.append(token['orth']) words.append(token['orth'])
ids.append(i) ids.append(i)
tags.append(token['tag']) tags.append(token.get('tag','-'))
heads.append(token['head'] + i) heads.append(token.get('head',0) + i)
labels.append(token['dep']) labels.append(token.get('dep','ROOT'))
# Ensure ROOT label is case-insensitive # Ensure ROOT label is case-insensitive
if labels[-1].lower() == 'root': if labels[-1].lower() == 'root':
labels[-1] = 'ROOT' labels[-1] = 'ROOT'