改进的VSM算法及其在FAQ中的应用  

Improved VSM Algorithm and Its Application in FAQ

作　　者：郑诚[1] 李清[1] 刘福君[1] 

机构地区：[1]安徽大学计算机科学与技术学院,合肥230039

出　　处：《计算机工程》2012年第17期201-204,共4页Computer Engineering

基　　金：安徽省自然科学基金资助项目(11040606M133)

摘　　要：现有的句子相似度算法的准确率较低。为此,提出一种改进的向量空间模型算法。在传统的向量空间模型中添加语义信息和句法信息,将其运用到句子相似度计算中,设计实现金融领域的FAQ自动问答系统,通过改进算法在FAQ中进行句子相似度计算,获取用户问题的答案。实验结果证明,该算法具有较高的准确率。The accuracy of the existing sentence similarity algorithm needs to be improved, so this paper improves Vector Space ModeI（VSM） algorithm, adds some syntactic information and semantic information in the traditional VSM for computing sentence similarity. Meanwhile, it designs and realizes a financial Frequently Asked Question（FAQ） question answering system. The system computes sentence similarity by the improved VSM algorithm and returns the answer of users＇ question. Experimental result shows that this algorithm has higher accuracy in computing sentence similarity.

关 键 词：句子相似度 向量空间模型 自动问答系统 索引 分词 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]