Conference Proceedings
Non-Linear Text Regression with a Deep Convolutional Neural Network
Z Bitvak, T COHN
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Short Papers) | The Association for Computational Linguistics | Published : 2015
DOI: 10.3115/v1/p15-2030
Open access
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 pa-rameters, this model can be trained on only a thousand documents, resulting in a 40% relative improvement over sparse lin-ear models, the previous state of the art. Further, this method is flexible allowing for easy incorporation of side information such as document meta-data. Finally we present a novel technique for interpreting the effect of different text inputs on this complex non-linear model.