基于翻译模型的查询会话检测方法研究

A Translation Model Based Method for Query Session Detection

查询会话检测的目的是确定用户为了满足某个特定需求而连续提交的相关查询。查询会话检测对于查询日志分析以及用户行为分析来说是非常有用的。传统的查询会话检测方法大都基于查询词的比较,无法解决词语不匹配问题(vocabulary-mismatch problem)——有些主题相关的查询之间并没有相同的词语。为了解决词语不匹配问题,我们在该文提出了一种基于翻译模型的查询会话检测方法,该方法将词与词之间的关系刻画为词与词之间的翻译概率,这样即使词与词之间没有相同的词语,我们也可以捕捉到它们之间的语义关系。同时,我们也提出了两种从查询日志中估计词翻译概率的方法,第一种方法基于查询的时间间隔,第二种方法基于查询的点击URLs。实验结果证明了该方法的有效性。

Query session detection is critical for query log analysis and user behavior characterization. It aims at iden- tifying the consecutive queries submitted by a user for the same information need. Traditional query session detection methods are based on lexical comparisons, which often suffer from the vocabulary-mismatch problem（i, e, the topi- cally related queries may not share any common words）. To resolve the issue, this paper proposes a translation model based method for query session detection, which can model the relationship between words as word transla- tion probability. In this way our method can capture the relatedness between queries even they do not share any com- mon words. Furthermore, we also propose two approaches for generating training data from web query log for translation probability estimation. The first approach is based on time gap between queries and the second is based on the clicked URI.s of queries. Experimental results show that our method can significantly outperform the base lines.