zxgineng / deepnlp Goto Github PK

非常感谢作者的项目，写的十分精彩，只是您同时可以提供一些用来试验的训练数据集吗？而不是简单的很少量的demo

Thanks for your amazing work.. I am NLP developer in HK.

May I ask u one question about the pre-processed step?

U mentioned :
Process raw data

Put data(.txt) in dataset_path
Data must follow the format of example data
Put wordvec(.txt) in processed_path

The wordvec(.txt) file is the pretrained word2vec file we downloaded from external parties or the algo will generate it by itself?

Thanks a lot