Hierarchical Convolutional Attention Networks for Text Classification

Abstract

Recent work in machine translation has demonstrated that self-attention mecha- nisms can be used in place of recurrent neural networks to increase training speed without sacrificing model accuracy. We propose combining this approach with the benefits of convolutional filters and a hi- erarchical structure to create a document classification model that is both highly ac- curate and fast to train – we name our method Hierarchical Convolutional Atten- tion Networks. We demonstrate the effec- tiveness of this architecture by surpassing the accuracy of the current state-of-the-art on several classification tasks while being twice as fast to train.