Very Deep Convolutional Networks for Text Classification

Understand

The dominant approach for many NLP tasks are recurrent neural networks, in particular LSTMs, and convolutional neural networks.

• However, these architectures are rather shallow in comparison to the deep convolutional networks which have pushed the state-of-the-art in computer vision.
• We present a new architecture (VDCNN) for text processing which operates directly at the character level and uses only small convolutions and pooling operations.
• We are able to show that the performance of this model increases with depth: using up to 29 convolutional layers, we report improvements over the state-of-the-art on several public text classification tasks.