A novel CNN-based method for Question Classification in Intelligent Question Answering

Abstract

Sentence classification, which is the foundation of the subsequent text-based processing, plays an important role in the intelligent question answering (IQA). Convolutional neural networks (CNN) as a kind of common architecture of deep learning, has been widely used to the sentence classification and achieved excellent performance in open field. However, the class imbalance problems and fuzzy sentence feature problem are common in IQA. With the aim to get better performance in IQA, this paper proposes a simple and effective method by increasing generalization and the diversity of sentence features based on simple CNN. In proposed method, the professional entities could be replaced by placeholders to improve the performance of generalization. And CNN reads sentence vectors from both forward and reverse directions to increase the diversity of sentence features. The testing results show that our methods can achieve better performance than many other complex CNN models. In addition, we apply our method in practice of IQA, and the results show the method is effective.