文本分类模型,Keras-TensorFlow
|-- data
|-- raw_df.pkl # intent_train_df,intent_test_df,reason_train_df,reason_test_df
|-- token2index.pkl # intent_word2index,
|-- models
|-- attention.py # attention,self attentive
|-- capsule.py # capsule net
|-- cnn.py # cnn, DPCNN
|-- configs.py # models configuration
|-- layers.py # customize layer
|-- model.py # base model
|-- rcnn.py # rcnn,crnn
|-- utils
|-- data_process.py # 处理数据
|-- dataset.py # 数据读取
|-- number.py # 处理文本中的数字
|-- score.py # 官方评估代码
|-- word_vectors
|-- word_embedding.py # pretrained word2vec
|-- inference.py # 少量数据验证
|-- main.py # 模型训练和测试
|-- postprocessing.py # 生成提交结果
|-- preprocessing.py # 预处理
- Joint embedding of words and labels for text classification ACL 2018
- A structured self-attentive sentence embedding ICLR 2017
- Hierarchical attention networks for Document classification NAACL 2016
- Deep Pyramid Convolutional Neural Networks for Text Categorization ACL 2017
- Document Modeling with Gated Recurrent Neural Network for Sentiment Classification ACL2015
- Recurrent Convolutional Neural Networks for Text Classification AAAI 2015
- Character-level Convolutional Networks for Text Classification. NIPS 2015
- Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms ACL2018
- python preprocessing.py 为NN模型预处理数据
- python main.py --mode train 训练NN模型
- python main.py --mode test 测试集预测输出
- 整理代码