面向特定领域自动问答系统的语句相似度计算  

Sentence Similarity Computing in Question Answering System for Specific Domain

作　　者：李健[1] 郑诚[1] 代宁[1] 

机构地区：[1]安徽大学计算机科学与技术学院,安徽合肥230039

出　　处：《合肥师范学院学报》2015年第6期38-41,共4页Journal of Hefei Normal University

基　　金：安徽省高校自然科学研究重点项目(KJ2013A020)资助;安徽大学科研训练计划资助

摘　　要：本文针对教务管理系统学生选课自动问答系统,提出一种语句相似度计算方法。该方法先采用基于布尔型VSM掩码的方法实现问题的初分类,再采用改进的编辑距离算法计算句子相似度来判断FAQ库的匹配,从而使系统返回问题的答案。实验结果表明该方法可行。The technique of sentence similarity computing in question answering system for students＇ course selection in the educational administration is presented. Firstly, preliminary classification is implemented by using a method based on VSM mask of Boolean. Secondly, sentence similarity computing is carried out through the improved editting distance algorithm. Finally the best answer of the problem is returned. The experimental results show that the method is feasible.

关 键 词：问答系统 向量空间模型 编辑距离 相似度计算 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]