https://github.com/mhcao916/NER_Based_on_BERT

this project is based on google bert model, which is a Chinese NER
https://github.com/mhcao916/NER_Based_on_BERT

Last synced: 13 days ago
JSON representation

this project is based on google bert model, which is a Chinese NER

• Host: GitHub
• URL: https://github.com/mhcao916/NER_Based_on_BERT
• Owner: mhcao916
• Created: 2018-12-02T07:00:25.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2018-12-02T08:24:20.000Z (over 6 years ago)
• Last Synced: 2024-11-02T23:32:31.394Z (5 months ago)
• Language: Python
• Size: 886 KB
• Stars: 4
• Watchers: 2
• Forks: 2
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-bert - mhcao916/NER_Based_on_BERT
• awesome-transformer-nlp - mhcao916/NER_Based_on_BERT - This project is based on Google BERT model, which is a Chinese NER. (Tasks / Named-Entity Recognition (NER))

README

        
本模型是基于google bert Chinese Based pre-trained model 进行fine-tuning，进行的中文命名实体识别实验

训练模型：

python cmh_bert_ner.py

我所使用的是google Chinese Based预训练模型进行fine-tuning的，在google官网下载；根据需要，自行更改模型的相关训练参数

测试效果：

python evaluate.py

本人所使用数据是基于旅游游记的数据，模型指标如下：

eval_f = 0.84716296

eval_precision = 0.8513407

eval_recall = 0.84808767

global_step = 31140

loss = 0.09112783

参考：英文实体识别： https://github.com/kyzhouhzau/BERT-NER