Non-Linear Text Regression with a Deep Convolutional Neural Network

Abstract

Text regression has traditionally been tackled using linear models. Here we present a non-linear method based on a deep convolutional neural network. We show that despite having millions of parameters, this model can be trained on only a thousand documents, resulting in a 40% relative improvement over sparse linear models, the previous state of the art… (More)

Topics

6 Figures and Tables

Statistics

05010015020162017
Citations per Year

Citation Velocity: 51

Averaging 51 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.

Cite this paper

@inproceedings{Bitvai2015NonLinearTR, title={Non-Linear Text Regression with a Deep Convolutional Neural Network}, author={Zsolt Bitvai and Trevor Cohn}, booktitle={ACL}, year={2015} }