Very Deep Convolutional Networks for Text Classification

06/06/2016
by   Alexis Conneau, et al.
0

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. To the best of our knowledge, this is the first time that very deep convolutional nets have been applied to text processing.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/04/2015

Character-level Convolutional Networks for Text Classification

This article offers an empirical exploration on the use of character-lev...
research
01/28/2019

Squeezed Very Deep Convolutional Neural Networks for Text Classification

Most of the research in convolutional neural networks has focused on inc...
research
11/16/2016

A Way out of the Odyssey: Analyzing and Combining Recent Insights for LSTMs

LSTMs have become a basic building block for many deep NLP models. In re...
research
12/02/2015

Rethinking the Inception Architecture for Computer Vision

Convolutional networks are at the core of most state-of-the-art computer...
research
12/20/2013

Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks

Recognizing arbitrary multi-character text in unconstrained natural phot...
research
11/19/2015

Mediated Experts for Deep Convolutional Networks

We present a new supervised architecture termed Mediated Mixture-of-Expe...
research
03/12/2017

Multiscale Hierarchical Convolutional Networks

Deep neural network algorithms are difficult to analyze because they lac...

Please sign up or login with your details

Forgot password? Click here to reset