Learning text representation using recurrent convolutional neural network with highway layers

TL;DR

This paper introduces a hybrid neural network model combining recurrent, convolutional, and highway layers for improved text representation, demonstrating superior performance in sentiment analysis and effective handling of long texts.

Contribution

The paper presents a novel staged hybrid RCNN with highway layers that enhances text representation and outperforms existing neural models in sentiment analysis.

Findings

Outperforms CNN, RNN, Bi-RNN in sentiment analysis

Effective in learning long text representations

Model handles varying sequence lengths well

Abstract

Recently, the rapid development of word embedding and neural networks has brought new inspiration to various NLP and IR tasks. In this paper, we describe a staged hybrid model combining Recurrent Convolutional Neural Networks (RCNN) with highway layers. The highway network module is incorporated in the middle takes the output of the bi-directional Recurrent Neural Network (Bi-RNN) module in the first stage and provides the Convolutional Neural Network (CNN) module in the last stage with the input. The experiment shows that our model outperforms common neural network models (CNN, RNN, Bi-RNN) on a sentiment analysis task. Besides, the analysis of how sequence length influences the RCNN with highway layers shows that our model could learn good representation for the long text.