kor-naver-ner-name / README.md
joon09's picture
Update README.md
2d8f6b4
ν•œκ΅­μΈ 이름 인식 λͺ¨λΈ
kor-bert fine-tuning λͺ¨λΈ
자주 μ•ˆμ“°λŠ” ν•œκΈ€μ΄λ¦„ κΈ°μ€€μœΌλ‘œ
생성기λ₯Ό λ§Œλ“€μ–΄μ„œ, 16만개의 ν•œκΈ€ 이름을 생성 ν›„ ν•™μŠ΅ν•œ λͺ¨λΈμž…λ‹ˆλ‹€.
ex) μ•ˆλ…•ν•˜μ„Έμš”. μž„μ€€μ˜μž…λ‹ˆλ‹€. -> μ•ˆλ…•ν•˜μ„Έμš”. ***μž…λ‹ˆλ‹€.
```python
from transformers import BertTokenizerFast, BertForTokenClassification
from transformers import pipeline
model_name = 'joon09/kor-naver-ner-name'
tokenizer = BertTokenizerFast.from_pretrained(model_name)
model = BertForTokenClassification.from_pretrained(model_name)
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
ner('μ•ˆλ…•ν•˜μ„Έμš”. μž„μ€€μ˜μž…λ‹ˆλ‹€.',grouped_entities=True,aggregation_strategy='average')
[{'entity_group': 'PER',
'score': 0.99999785,
'word': 'μž„',
'start': 7,
'end': 8},
{'entity_group': 'PER',
'score': 0.82035744,
'word': '##μ€€μ˜',
'start': 8,
'end': 10}]
```