oh201516 commited on
Commit
864cb91
·
verified ·
1 Parent(s): 03f139a

Update spaCy pipeline

Browse files
config.cfg CHANGED
@@ -48,7 +48,7 @@ upstream = "*"
48
 
49
  [components.normalizer_component]
50
  factory = "normalizer_component"
51
- norm_file = "normilization.json"
52
 
53
  [components.tok2vec]
54
  factory = "tok2vec"
 
48
 
49
  [components.normalizer_component]
50
  factory = "normalizer_component"
51
+ norm_file = null
52
 
53
  [components.tok2vec]
54
  factory = "tok2vec"
en_setec_mk_tv-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32b24f9fbb068cdd0818a7286c4afdd871eef0d64a5bb0ec99824e8a66f5d6b0
3
- size 5707744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa2fe9279a4fe64e62863259d1b3a8412df014f391706cd345415ea9776b3d27
3
+ size 5707735
normalizer_component.py CHANGED
@@ -73,6 +73,6 @@ class NormalizerComponent(object):
73
  def __call__(self, doc):
74
  for ent in doc.ents:
75
  for match_id, start, end in self.matcher(self.nlp.make_doc(ent._.text)):
76
- match_id_string = nlp.vocab.strings[match_id]
77
  ent._.text = match_id_string.strip()
78
  return doc
 
73
  def __call__(self, doc):
74
  for ent in doc.ents:
75
  for match_id, start, end in self.matcher(self.nlp.make_doc(ent._.text)):
76
+ match_id_string = self.nlp.vocab.strings[match_id]
77
  ent._.text = match_id_string.strip()
78
  return doc