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。

关键词: 句子相似度, 向量空间模型, 自动问答系统, 索引, 分词

Abstract: The accuracy of the existing sentence similarity algorithm needs to be improved, so this paper improves Vector Space Model(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.

Key words: sentence similarity, Vector Space Model(VSM), automatic question answering system, index, word segmentation

中图分类号: 

• TP301.6