You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
yh dc7f8ef8d4 bug fix 6 years ago
..
__init__.py changes to trainer, tester, preprocessor, etc. 7 years ago
batch.py - 添加pos_tagger API, pipeline跑通 6 years ago
dataset.py bug fix 6 years ago
field.py fix fieldarray, dataset 6 years ago
fieldarray.py Sampler中增加了一个BucketSampler, CWS的训练基本可以实现 6 years ago
instance.py - 修改pos tag训练脚本,可以跑 6 years ago
loss.py Merge Preprocessor and DataSet 6 years ago
metrics.py - 添加pos_tagger API, pipeline跑通 6 years ago
optimizer.py Text classification interface is ready. 7 years ago
predictor.py - add interfaces for pos_tagging API 6 years ago
preprocess.py remove unused codes; add more tests 6 years ago
sampler.py 当前版本分词准确率已达正常分词分数 6 years ago
tester.py - 添加pos_tagger API, pipeline跑通 6 years ago
trainer.py - 添加pos_tagger API, pipeline跑通 6 years ago
vocabulary.py update parser, fix bugs varrnn & vocab 6 years ago

一款轻量级的自然语言处理(NLP)工具包,目标是减少用户项目中的工程型代码,例如数据处理循环、训练循环、多卡运行等

Python Jupyter Notebook Text CSV Markdown