After the exercise of building convolutional, RNN, sentence level attention RNN, finally I have come to implement Hierarchical Attention Networks for Document Classification. I’m very thankful to Keras, which make building this project painless. The custom layer is very powerful and flexible to build your custom logic to embed into the existing frame work. Functional API makes the Hierarchical InputLayers very easy to implement.
Please note that all exercises are based on Kaggle’s IMDB dataset.
文件分类的分层注意网络
在构建卷积运算后，RNN，句级关注的 RNN，最后我来实现文档分类的分层注意网络。 我非常感谢Keras，这使得这个项目无痛。 自定义层是非常强大和灵活的，以构建您的自定义逻辑嵌入到现有的框架工作。 功能API使层次输入层很容易实现。
论文：https://www.cs.cmu.edu/~diyiy/docs/naacl16.pdf
项目：https://github.com/richliao/textClassifier
项目：https://github.com/ilivans/tf-rnn-attention
更多 Tensorflow 教程：http://www.tensorflownews.com
