KoELECTRA-small-v3-modu-ner

This model is a fine-tuned version of monologg/koelectra-small-v3-discriminator on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1431
• Precision: 0.8232
• Recall: 0.8449
• F1: 0.8339
• Accuracy: 0.9628

Model description

태깅 시스템 : BIO 시스템

• B-(begin) : 개체명이 시작할 때
• I-(inside) : 토큰이 개체명 중간에 있을 때
• O(outside) : 토큰이 개체명이 아닐 경우

한국정보통신기술협회(TTA) 대분류 기준을 따르는 15 가지의 태그셋

Intended uses & limitations

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("Leo97/KoELECTRA-small-v3-modu-ner")
model = AutoModelForTokenClassification.from_pretrained("Leo97/KoELECTRA-small-v3-modu-ner")
ner = pipeline("ner", model=model, tokenizer=tokenizer)

example = "서울역으로 안내해줘."
ner_results = ner(example)
print(ner_results)

Training and evaluation data

개체명 인식(NER) 모델 학습 데이터 셋

• 문화체육관광부 > 국립국어원 > 모두의 말뭉치 > 개체명 분석 말뭉치 2021
• https://corpus.korean.go.kr/request/reausetMain.do

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 15151
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.27.4
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3