yongzhang-hz/chinese_sentence_classification

Implementation of TextCNN, TextRNN, RCNN, FastText with Pytorch(Pytorch实现中文句子分类)

Chinese_Sentence_Classification

Implementation of TextCNN, TextRNN, RCNN, FastText with Pytorch
Pytorch 中文文本分类模型

Prerequisites

Python >= 3.5
Pytorch >= 1.1.0
torchtext >= 0.3.1
jieba >= 0.39

Data organizer

Train and test data are organized in the following style

Query, label

Models

TextCNN

FastText

TextRNN

RCNN

Train

In each folder, you could train model in 4 ways:

Random Initialize Word Embedding
python main.py

Use pre-trained Word Embedding (freeze)
python main.py -static=true

Use pre-trained Word Embedding (not freeze)
python main.py -static=true -non-static=true

Use pre-trained Word Embedding (multi-channel : free + not freeze)
python main.py -static=true -non-static=true -multichannel=true

Word Embeddings

Chinese-Word-Vectors

Reference

Text-Classification-Models-Pytorch
chinese_text_cnn