New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

7.30——开源项目pycorrector分析（二） #14

Open

li-aolong opened this issue Jul 30, 2019 · 0 comments

Labels

GEC NLP 开源项目

Owner

li-aolong commented Jul 30, 2019

代码较多，看起来比较耗费时间

基于深度模型的方法——rnn_lm

数据预处理
- config.py文件提供了初始化配置
- 使用preprocess.py文件进行处理，对CGED三年的比赛数据进行解析，将字符分割并保存
模型设计
- 由rnn_lm_model文件构造单元函数可选：rnn，gru或lstm
- 每个rnn单元默认有128个节点，共2层
训练
- data_reader.py文件将文本的字符转换成固定的序号，并保存字符-序号对照表
- train.py文件生成小批量数据，如batch_size大小为128
- 训练数据，并保存模型
infer.py与lm.py文件使用训练好的模型进行测试

The text was updated successfully, but these errors were encountered:

li-aolong added GEC NLP 开源项目 labels

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment