An important component of question answering systems is question classification. The task of question classification is to predict the entity type of the answer of a natural language question. For example for the given question of what is the capital of the Netherlands?, the task of question classification is to classify this question to the category city since the answer type of this question is of type city. Question classification is typically done using machine learning techniques. Different lexical, syntactical and semantic features can be extracted from a question. In this work we introduce two new semantic features which improve the accuracy of classification. Furthermore, we developed a weighed approach to optimally combine different features. We also applied Latent Semantic Analysis (LSA) technique to reduce the large feature space of questions to a much smaller and efficient feature space. Our experimental results show that our approach is successful.

Babak Loni did his MSc. of Computer Science in Delft University of Technology, Netherlands, and his BSc. of Computer Science in Amirkabir University of Technology, Iran. His main expertise is Natural Language Processing. He has also successful records in Software Engineering. You can find more info about him in: www.babak-loni.com