KoELECTRA-small-v3-privacy-ner
This model is a fine-tuned version of monologg/koelectra-small-v3-discriminator on a synthesized privacy dataset. It achieves the following results on the evaluation set:
- f1 = 0.9998728608843798
- loss = 0.05310981854414328
- precision = 0.9999237126509853
- recall = 0.9998220142897098
Model description
ํ๊น ์์คํ : BIO ์์คํ
- -B(begin) : ๊ฐ์ฒด๋ช ์ด ์์ํ ๋
- -I(inside) : ํ ํฐ์ด ๊ฐ์ฒด๋ช ์ค๊ฐ์ ์์ ๋
- O(outside) : ํ ํฐ์ด ๊ฐ์ฒด๋ช ์ด ์๋ ๊ฒฝ์ฐ
12๊ฐ์ง ํ๊ตญ์ธ ๊ฐ์ธ์ ๋ณด ํจํด์ ๋ํ ํ๊ทธ์
๋ถ๋ฅ | ํ๊ธฐ | ์ ์ |
---|---|---|
PERSON | PER | ํ๊ตญ์ธ ์ด๋ฆ |
LOCATION | LOC | ํ๊ตญ ์ฃผ์ |
RESIDENT REGISTRATION NUMBER | RRN | ํ๊ตญ์ธ ์ฃผ๋ฏผ๋ฑ๋ก๋ฒํธ |
EMA | ์ด๋ฉ์ผ | |
ID | ID | ์ผ๋ฐ ๋ก๊ทธ์ธ ID |
PASSWORD | PWD | ์ผ๋ฐ ๋ก๊ทธ์ธ ๋น๋ฐ๋ฒํธ |
ORGANIZATION | ORG | ์์ ๊ธฐ๊ด |
PHONE NUMBER | PHN | ์ ํ๋ฒํธ |
CARD NUMBER | CRD | ์นด๋๋ฒํธ |
ACCOUNT NUMBER | ACC | ๊ณ์ข๋ฒํธ |
PASSPORT NUMBER | PSP | ์ฌ๊ถ๋ฒํธ |
DRIVER'S LICENSE NUMBER | DLN | ์ด์ ๋ฉดํ๋ฒํธ |
How to use
You can use this model with Transformers pipeline for NER.
from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline
tokenizer = AutoTokenizer.from_pretrained("amoeba04/test1")
model = AutoModelForTokenClassification.from_pretrained("amoeba04/test1")
ner = pipeline("ner", model=model, tokenizer=tokenizer)
example = "์ง๋์ฃผ, ํ๊ธธ๋ ์จ๋ ์์ธํน๋ณ์ ๊ฐ๋จ๊ตฌ์ ์์นํ ํ
ํค๋๋ก 101๋น๋ฉ์์ ์งํ๋ IT ์ปจํผ๋ฐ์ค์ ์ฐธ์ํ์ต๋๋ค."
ner_results = ner(example)
print(ner_results)
์ถ๋ ฅ: "PER-B, PER-B ์จ๋ LOC-BLOC-ILOC-I LOC-ILOC-I LOC-ILOC-I LOC-ILOC-I LOC-ILOC-ILOC-I์์ ์งํ๋ IT ์ปจํผ๋ฐ์ค์ ์ฐธ์ํ์ต๋๋ค."
Training and evaluation data
์์ฒด ์ ์ํ ํ๊ตญ์ธ ๊ฐ์ธ์ ๋ณด ํจํด ๊ธฐ๋ฐ ๊ฐ์ฒด๋ช ์ธ์ (NER) ๋ฐ์ดํฐ์
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 512
- eval_batch_size: 1024
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 21
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for amoeba04/koelectra-small-v3-privacy-ner
Base model
monologg/koelectra-small-v3-discriminator