@InProceedings{conneau-EtAl:2017:EACLlong,
  author    = {Conneau, Alexis  and  Schwenk, Holger  and  Barrault, Lo\"{i}c  and  Lecun, Yann},
  title     = {Very Deep Convolutional Networks for Text Classification},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {1107--1116},
  abstract  = {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 the
	depth: using up to 29 convolutional layers, we report improvements
	over the state-of-the-art on several public text classification tasks.               
	     
	To the
	best of our knowledge, this is the first time that very deep convolutional nets
	have been applied to text processing.},
  url       = {http://www.aclweb.org/anthology/E17-1104}
}