TY - JOUR
AU - 
AB - Very Deep Convolutional Networks for Text Classification Alexis Conneau Holger Schwenk Yann Le Cun Facebook AI Research Facebook AI Research Facebook AI Research aconneau@fb.com schwenk@fb.com yann@fb.com Lo¨ıc Barrault LIUM, University of Le Mans, France loic.barrault@univ-lemans.fr Abstract terest in the research community and they are sys- tematically applied to all NLP tasks. However, The dominant approach for many NLP while the use of (deep) neural networks in NLP tasks are recurrent neural networks, in par- has shown very good results for many tasks, it ticular LSTMs, and convolutional neural seems that they have not yet reached the level to networks. However, these architectures outperform the state-of-the-art by a large margin, are rather shallow in comparison to the as it was observed in computer vision and speech deep convolutional networks which have recognition. pushed the state-of-the-art in computer vi- Convolutional neural networks, in short Con- sion. We present a new architecture (VD- vNets, are very successful in computer vision. In CNN) for text processing which operates early approaches to computer vision, handcrafted directly at the character level and uses features were used, for instance “scale-invariant only small convolutions and pooling oper- feature transform (SIFT)” (Lowe, 2004), followed ations. We are able 
TI - Very Deep Convolutional Networks for Text Classification
JF - Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
DO - 10.18653/v1/e17-1104
DA - 2017-01-01
UR - https://www.deepdyve.com/lp/unpaywall/very-deep-convolutional-networks-for-text-classification-13DjVbyWHn
DP - DeepDyve
ER -