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

* When encoding POS/NER tags, accept '-' as a missing value

This commit is contained in:
Matthew Honnibal 2014-11-07 04:42:31 +11:00
parent 949a6245f9
commit 68d1cdad62
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/pos_util.py
View File

@ -36,6 +36,8 @@ def read_gold(file_, tag_list, col):
return golds return golds
def _encode_pos(tag, tag_ids, tag_list): def _encode_pos(tag, tag_ids, tag_list):
if tag == '-':
return 0
if tag not in tag_ids: if tag not in tag_ids:
tag_ids[tag] = len(tag_list) tag_ids[tag] = len(tag_list)
tag_list.append(tag) tag_list.append(tag)