信息检索中相似度计算的新方法

New Approach to Similarity Computing in Information Retrieval

提出一种计算相似度的新方法,在计算相似度时考虑到查询词出现在文档中不同部分对相似度计算的不同贡献,即不同的权重系数,并用遗传算法确定各个权重系数.实验结果表明,这种新方法在信息检索中在计算相似度时比传统的向量空间模型方法具有更好的效果.

Similarity computing plays an important role in information retrieval. In this paper, a new approach to computing similarity is proposed. When we compute similarity, different contribution, namely weighted coefficients of different position of words in different part of the document are considered. And we use Genetic Algorithm to consider the weighted coefficients. Experimental results show that the new method has more effect than Vector Space Model.