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.
Very Deep Convolutional Networks for Text Classification
Holger Schwenk,Loïc Barrault,Alexis Conneau,Yann LeCun
Published 2016 in Conference of the European Chapter of the Association for Computational Linguistics
ABSTRACT
PUBLICATION RECORD
- Publication year
2016
- Venue
Conference of the European Chapter of the Association for Computational Linguistics
- Publication date
2016-06-06
- Fields of study
Computer Science
- Identifiers
- External record
- Source metadata
Semantic Scholar
CITATION MAP
EXTRACTION MAP
CLAIMS
- No claims are published for this paper.
CONCEPTS
- No concepts are published for this paper.
REFERENCES
Showing 1-27 of 27 references · Page 1 of 1