TY - GEN
T1 - Very deep convolutional networks for text classification
AU - Conneau, Alexis
AU - Schwenk, Holger
AU - Cun, Yann Le
AU - Barrault, Löc
N1 - Publisher Copyright:
© 2017 Association for Computational Linguistics.
PY - 2017
Y1 - 2017
N2 - 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-ofthe- 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.
AB - 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-ofthe- 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.
UR - http://www.scopus.com/inward/record.url?scp=85021673250&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85021673250&partnerID=8YFLogxK
U2 - 10.18653/v1/e17-1104
DO - 10.18653/v1/e17-1104
M3 - Conference contribution
AN - SCOPUS:85021673250
T3 - 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference
SP - 1107
EP - 1116
BT - Long Papers - Continued
PB - Association for Computational Linguistics (ACL)
T2 - 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017
Y2 - 3 April 2017 through 7 April 2017
ER -