关键词: 相似度计算, 模式分类, 上下文信息, 问答系统

Abstract: At present, question answering system based on Frequently Asked Questions（FAQ） for restricted domains is a research focus in the field of natural language processing due to its practicality. The similarity measure between questions plays a very important role in one question answering system. The traditional questions similarity measure technologies have unsatisfactory effects for those questions with context information. A rule-based question pattern classification algorithm is proposed for dividing all questions into two categories: Simple Mode Questions（SMQs） and Context Mode Questions（CMQs）. Then, a similarity measure method for CMQs is presented in which the similarities between context information and that between questions are combined together. The experimental results show that both precision and recall rate of the proposed question pattern classification method exceed 90%, and the accuracy of similarity measure for context mode questions reaches 74.3% with lower time complexity.

Key words: similarity measure, pattern classification, context information, question answering system