网络表格间的快照关系发现

Detecting Snapshots for Web Tables

近年来,互联网上涌现出大量结构化的表格数据,网络表格的价值不仅在于数据本身,还在于数据之间的关系。只有探测出表格之间潜在的关系,方能更好地利用这些结构化数据。因此提出发现网络表格间的快照关系,并给出发现快照关系的框架以及检测与给定表之间满足某种匹配关系的快照表的算法,快照表可用于优化查询以及在大数据环境下实时地返回部分查询结果。提出了基于实体和属性重合度的评分方法,并引入实体新鲜度的概念,使得算法在快照关系的发现过程中更多地关注能提供新鲜实体的表;与此同时,基于Bayes模型的表格内容增强算法能更加准确地判断属性列上值的一致性,从而提高快照关系发现的准确率。大量实验表明,该评分模型能发现高质量的快照表,且在快照的查询精度和召回率上表现出色。

In recent years,a large number of structured tabular data have emerged on the Internet constantly.However,the value of Web tables depends not only on the data itself,but also on the relatedness between the data.Only when the potential relatedness between them is detected,can these structured data be fully utilized.We proposed a new type of relatedness between Web tables called snapshot relationship,and a framework for capturing snapshots that meet a certain matching condition with a given table.The snapshots are beneficial for query optimization,and also helpful for returning partial results rapidly when querying on big data.The relatedness between an original Web table and its snapshot can be computed based on entity consistency and schema consistency.In order to assign high weights on tables which provide more fresh entities,the concept of entity freshness was introduced into our scoring method.Meanwhile,the content consistency of Web tables can be enhanced by applying Bayesian analysis to our relatedness capturing framework.As a consequence,accuracy of finding snapshots is improved.Extensive experiments demonstrate that the algorithms can capture snapshots with high quality,and perform well in query precision and recall.