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

2014-11-07 04:42:31 +11:00 · 2014-11-07 04:42:31 +11:00 · 68d1cdad62
parent 949a6245f9
commit 68d1cdad62
1 changed files with 2 additions and 0 deletions
--- a/spacy/pos_util.py
+++ b/spacy/pos_util.py
@ -36,6 +36,8 @@ def read_gold(file_, tag_list, col):
    return golds

 def _encode_pos(tag, tag_ids, tag_list):
+    if tag == '-':
+        return 0
    if tag not in tag_ids:
        tag_ids[tag] = len(tag_list)
        tag_list.append(tag)