Improving query suggestion through noise filtering and query length prediction
Improving query suggestion through noise filtering and query length prediction
复制标题
通过噪声过滤和查询长度预测改进查询建议
DOI：
--
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Jianhui Li
中科院分区：
文献类型：
--
作者：
Liang Wu;Bin Cao;Yuanchun Zhou;Jianhui Li
基于聚类的方法通常用于 Web 搜索引擎中的查询建议。聚类对于减少数据的稀疏性很有用。然而，它也引入了噪声并忽略了搜索会话中查询细化的顺序信息。在本文中，我们提出从两个角度改进基于集群的查询建议：过滤掉不相关的查询候选者和预测细化方向。我们观察到两个主要的改进行为。一是简化原始查询，二是指定它。两者都可以通过在对候选者进行排名时预测查询的长度（术语数量）来建模。对商业搜索引擎的真实查询日志的两个实验结果证明了所提出方法的有效性。
Clustering-based methods are commonly used in Web search engines for query suggestion. Clustering is useful in reducing the sparseness of data. However, it also introduces noises and ignores the sequential information of query refinements in search sessions. In this paper, we propose to improve cluster based query suggestion from two perspectives: filtering out unrelated query candidates and predicting the refinement direction. We observe two major refinements behaviors. One is to simplify the original query and the other is to specify it. Both could be modeled by predicting the length (number of terms) of queries when candidates are being ranked. Two experimental results on the real query logs of a commercial search engine demonstrate the effectiveness of the proposed approaches.