A C-LSTM Neural Network for Text Classification

Neural network models have been demon- strated to be capable of achieving remarkable performance in sentence and document mod- eling. 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 ex- tract a sequence of higher-level phrase repre- sentations, 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 se- mantics. We evaluate the proposed archi- tecture on sentiment classification and ques- tion classification tasks. The experimental re- sults show that the C-LSTM outperforms both CNN and LSTM and can achieve excellent performance on these tasks.