摘要： 实用、高效的Web搜索引擎依赖于有效的检索算法,而如何提高检索精度是检索算法的关键。该文论述了一种在最短片段算法的基础上进行改进后的检索算法。它是基于扩展布尔检索框架的检索算法。还给出了新的算法在2001文本检索会议(TREC 10) 的Web语料上的实验数据。实验结果表明,新的算法比原始的算法在检索精度上有所提高。

关键词: Web检索, 搜索引擎, 最短片段算法, 扩展布尔检索

Abstract: Practical and efficient Web search engine depends on effective information retrieval algorithm. How to improve the precision of searching result is one of the key factors to information retrieval algorithm. This paper describes a modified search algorithm based on shortest extent algorithm. This modified algorithm is based on ramework of extended Boolean retrieval algorithm. Experiments data are also given on the 2001 text retrieval conference (TREC 10) Web corpus. Data show that modified algorithm has a higher searching result precision than original shortest extent algorithm.

中图分类号: 

• TP393.09