Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/pengming617/bert_textMatching
利用预训练的中文模型实现基于bert的语义匹配模型 数据集为LCQMC官方数据
https://github.com/pengming617/bert_textMatching
Last synced: 6 days ago
JSON representation
利用预训练的中文模型实现基于bert的语义匹配模型 数据集为LCQMC官方数据
- Host: GitHub
- URL: https://github.com/pengming617/bert_textMatching
- Owner: pengming617
- Created: 2019-03-13T06:42:22.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2019-12-19T06:23:17.000Z (almost 5 years ago)
- Last Synced: 2024-08-02T08:10:10.903Z (3 months ago)
- Language: Python
- Homepage:
- Size: 6.27 MB
- Stars: 193
- Watchers: 3
- Forks: 53
- Open Issues: 8
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-bert - pengming617/bert_textMatching
README
利用bert预训练的中文语言模型进行文本匹配
训练脚本 train.sh
批量测试脚本 predict.sh
利用模型进行单条语句测试 intent.py
chinese_L-12_H-768_A-12为预训练的相关模型和词典
data文件夹中为训练语料,验证语料,测试语料 数据集为LCQMC官方数据
参数说明:
max_seq_length sentence的最大长度(字)
train_batch_size batch_size的大小max_seq_length = 50
eval_accuracy = 0.87207
test_accuracy = 0.86272max_seq_length = 40
eval_accuracy = 0.88093615
test_accuracy = 0.86256