Tencent / NeuralNLP-NeuralClassifier

An Open-source Neural Hierarchical Multi-label Text Classification Toolkit

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

what is the doc_char dict ?

wuyou521 opened this issue · comments

Use dataset to generate dict.
Size of doc_label dict is 7
Size of doc_token dict is 25028
Size of doc_char dict is 34
Size of doc_token_ngram dict is 0
Size of doc_keyword dict is 6242
Size of doc_topic dict is 0
Shrink dict over.
Size of doc_label dict is 7
Size of doc_token dict is 10880
Size of doc_char dict is 33
Size of doc_token_ngram dict is 0
Size of doc_keyword dict is 6242
Size of doc_topic dict is 0

上面下面的doc_char dict不一样

这个内容可以在dict_rcv1中找到
主要用来帮助你找到你的各种词的统计量