Question Classification Based on Hybrid Neural Networks
Zhongcheng Zhou, Zhu Xiang, Zhonghe He, Yin-chuan QU · 2016
Question classification is an important step in question answering system.There are many previous work based on machine learning about question classification.Although they are effective and practical, most of them require finding specific features to train the designed classifier.So it cannot be in common use in all the situations.Recently, deep learning methods has shown its remarkable strength in natural language processing.Deep neural networks like CNN and LSTM are helpful for sentence classification.The CNN is able to extract high-level local features while the LSTM can remember and discard information according to the context.Thus we implement a Hybrid Neural Network to handle different parts of a query.Both CNN and LSTM are utilized to achieve question classification.We conduct experiments comparing with methods based on machine learning and deep learning.The experimental results show the effectiveness and efficiency of our methods. Related WorkThe Question Answering (QA) is a research activity which is related to Information Retrieval (IR) and NLP, but it is quite different from them in certain way.QA is a very practical activity and is