pustozerov commited on
Commit
b3d7e5c
·
1 Parent(s): 26cb077

Implemented optimized NER function.

Browse files
Files changed (1) hide show
  1. modules/nlp/nemo_ner.py +17 -0
modules/nlp/nemo_ner.py ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import re
2
+ from collections import Counter
3
+
4
+ from nemo.collections import nlp as nemo_nlp
5
+
6
+ new_config = nemo_nlp.models.TokenClassificationModel.from_pretrained(model_name="ner_en_bert", return_config=True)
7
+ new_config.dataset.num_workers = 0
8
+ pretrained_ner_model = nemo_nlp.models.TokenClassificationModel.from_pretrained(
9
+ model_name="ner_en_bert", override_config_path=new_config)
10
+
11
+
12
+ def detect_ner(input_string):
13
+ results = pretrained_ner_model.add_predictions([input_string.replace('[', '').replace(']', '')])[0]
14
+ print(results)
15
+ tags = re.findall('\[.*?]', results)
16
+ output_string = "Found named entities: " + str(dict(Counter(tags)))[1:-1]
17
+ return output_string