基于用户日志的查询扩展统计模型

A Statistical Query Expansion Model Based on Query Logs

信息检索长期存在着用词歧义性问题,在Web搜索上的表现更加突出.提出了一种基于用户查询日志的查询扩展统计模型,将用户查询中使用的词或短语与文档中出现的相应词或短语以条件概率的形式连接,利用贝叶斯公式挑选出文档中与该查询关联最紧密的词加入原查询,以达到扩展优化的目的.实验结果表明,该方法更适宜改进Web上的信息检索,相对传统的查询扩展算法可以大幅度提高查询精度.

Ambiguity of query terms has been a long-standing problem in information retrieval field, which becomes more serious in Web searching. A method for automatic query expansion based on query logs obtained from users?daily usage is suggested. This model establishes probabilistic relationship between terms in documents and in user queries through statistical learning from the log, and selects high-related expansion terms based on Bayesian theory. These expansion terms are added into the original query to formulate a new one in order to improve the effectiveness of retrieval. Experimental results show that this technique is more adaptive to Web searching, and can improve the precision of document retrieval markedly compared with conventional ones.