【GitHub项目推荐】文本分类最好的几个深度学习方法 TensorFlow 实践

【导读】文本分类是NLP中常见的任务，近几年来出现了很多基于深度学习相关的方法。比如TextCNN、Attention-Based Bidirection LSTM、对抗学习、自注意力机制等等。因此，进行文本分类这一简单的任务实践是学习不同深度网络比较好的方式，建议大家收藏和学习。

作者：TobiasLee

Github 链接：

https://github.com/TobiasLee/Text-Classification

Text-Classification （文本分类）

Implement some state-of-the-art text classification models with TensorFlow.

You can load the data with

dbpedia = tf.contrib.learn.datasets.load_dataset('dbpedia', test_with_fake_data=FLAGS.test_with_fake_data)

Paper: Attention Is All You Need

See multi_head.py

Use self-attention where Query = Key = Value = sentence after word embedding

Multihead Attention module is implemented by Kyubyong

Paper: Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN

IndRNNCell is implemented by batzener

Paper: Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification

See attn_bi_lstm.py

Paper: Hierarchical Attention Networks for Document Classification

See attn_lstm_hierarchical.py

Attention module is implemented by ilivans/tf-rnn-attention .

Paper: Adversarial Training Methods For Semi-Supervised Text Classification

See: adversrial_abblstm.py

Paper: Convolutional Neural Networks for Sentence Classification

See: cnn.py

Paper: RMDL: Random Multimodel Deep Learning for Classification

See: RMDL.py See: RMDL Github

Note: The parameters are not fine-tuned, you can modify the kernel as you want.

Model	Test Accuracy	Notes
Attention-based Bi-LSTM	98.23 %
HAN	89.15%	1080Ti 10 epochs 12 min
Adversarial Attention-based Bi-LSTM	98.5%	AWS p2 2 hours
IndRNN	98.39%	1080Ti 10 epochs 10 min
Attention is All Your Need	97.81%	1080Ti 15 epochs 8 min
RMDL	98.91%	2X Tesla Xp (3 RDLs)
CNN	To be tested	To be done