Convolutional recurrent neural network for question answering

Abstract

Question answering has become a very important task for natural language understanding as most natural language processing problems can be posed as a question answering problem. Recurrent neural network (RNN) is a standard baseline model for various sequence prediction tasks including question answering. Recurrent networks can represent global information for a long period of time but they do not preserve local information very well. To address this problem we propose a model which is a combination of recurrent and convolutional network that can be trained end to end using backpropagation. Our experiments on bAbI dataset demonstrate that this model can achieve significant improvement over RNN model for question answering task.