https://github.com/fooSynaptic/BERT_classifer_trial

BERT trial for chinese corpus classfication
https://github.com/fooSynaptic/BERT_classifer_trial

nlp-machine-learning text-classification text-entailment

Last synced: 6 days ago
JSON representation

BERT trial for chinese corpus classfication

• Host: GitHub
• URL: https://github.com/fooSynaptic/BERT_classifer_trial
• Owner: fooSynaptic
• Created: 2018-11-30T09:41:22.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2019-03-29T03:22:21.000Z (over 5 years ago)
• Last Synced: 2024-08-02T08:09:55.892Z (3 months ago)
• Topics: nlp-machine-learning, text-classification, text-entailment
• Language: Python
• Size: 116 KB
• Stars: 7
• Watchers: 3
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-bert - fooSynaptic/BERT_classifer_trial
• awesome-transformer-nlp - fooSynaptic/BERT_classifer_trial - BERT trial for Chinese corpus classfication. (Tasks / Classification)

README

        
# BERT_classifer_trial

BERT trial for chinese corpus classfication

Please download pretrained BERT chinise model from [Pretrained Chinese Model](https://storage.googleapis.com/bert_models/2018_11_03/chinese_L-12_H-768_A-12.zip)

Just run `launch.sh` then the fine-tune process will intial.

Please modify the path from `launch.sh` and the path of out_dir in the `run_classfier.py` script

If you want to do the inference, you need to prepare the test file and open do_predict in `run_classfier.py`.

Script `predict_eval.py` may help you evaluate the inference result.