joon09 commited on
Commit
2d8f6b4
β€’
1 Parent(s): bd612cb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -0
README.md CHANGED
@@ -2,6 +2,9 @@
2
 
3
  kor-bert fine-tuning λͺ¨λΈ
4
 
 
 
 
5
  ex) μ•ˆλ…•ν•˜μ„Έμš”. μž„μ€€μ˜μž…λ‹ˆλ‹€. -> μ•ˆλ…•ν•˜μ„Έμš”. ***μž…λ‹ˆλ‹€.
6
 
7
 
@@ -13,5 +16,18 @@ model_name = 'joon09/kor-naver-ner-name'
13
  tokenizer = BertTokenizerFast.from_pretrained(model_name)
14
  model = BertForTokenClassification.from_pretrained(model_name)
15
  nlp = pipeline("ner", model=model, tokenizer=tokenizer)
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  ```
17
 
 
2
 
3
  kor-bert fine-tuning λͺ¨λΈ
4
 
5
+ 자주 μ•ˆμ“°λŠ” ν•œκΈ€μ΄λ¦„ κΈ°μ€€μœΌλ‘œ
6
+ 생성기λ₯Ό λ§Œλ“€μ–΄μ„œ, 16만개의 ν•œκΈ€ 이름을 생성 ν›„ ν•™μŠ΅ν•œ λͺ¨λΈμž…λ‹ˆλ‹€.
7
+
8
  ex) μ•ˆλ…•ν•˜μ„Έμš”. μž„μ€€μ˜μž…λ‹ˆλ‹€. -> μ•ˆλ…•ν•˜μ„Έμš”. ***μž…λ‹ˆλ‹€.
9
 
10
 
 
16
  tokenizer = BertTokenizerFast.from_pretrained(model_name)
17
  model = BertForTokenClassification.from_pretrained(model_name)
18
  nlp = pipeline("ner", model=model, tokenizer=tokenizer)
19
+
20
+ ner('μ•ˆλ…•ν•˜μ„Έμš”. μž„μ€€μ˜μž…λ‹ˆλ‹€.',grouped_entities=True,aggregation_strategy='average')
21
+
22
+ [{'entity_group': 'PER',
23
+ 'score': 0.99999785,
24
+ 'word': 'μž„',
25
+ 'start': 7,
26
+ 'end': 8},
27
+ {'entity_group': 'PER',
28
+ 'score': 0.82035744,
29
+ 'word': '##μ€€μ˜',
30
+ 'start': 8,
31
+ 'end': 10}]
32
  ```
33