A C-LSTM Neural Network for Text Classification

TL;DR

This paper introduces C-LSTM, a unified neural network model that combines CNN and LSTM architectures to improve sentence representation and text classification performance.

Contribution

The paper proposes a novel C-LSTM model that integrates CNN and LSTM to capture both local phrase features and global sentence semantics.

Findings

C-LSTM outperforms standalone CNN and LSTM models.

The model achieves state-of-the-art results on sentiment and question classification.

C-LSTM effectively captures both local and global textual features.

Abstract

Neural network models have been demonstrated to be capable of achieving remarkable performance in sentence and document modeling. Convolutional neural network (CNN) and recurrent neural network (RNN) are two mainstream architectures for such modeling tasks, which adopt totally different ways of understanding natural languages. In this work, we combine the strengths of both architectures and propose a novel and unified model called C-LSTM for sentence representation and text classification. C-LSTM utilizes CNN to extract a sequence of higher-level phrase representations, and are fed into a long short-term memory recurrent neural network (LSTM) to obtain the sentence representation. C-LSTM is able to capture both local features of phrases as well as global and temporal sentence semantics. We evaluate the proposed architecture on sentiment classification and question classification tasks. The experimental results show that the C-LSTM outperforms both CNN and LSTM and can achieve excellent performance on these tasks.