使用CNF阻塞的作者姓名缩放消歧
Scaling Author Name Disambiguation with CNF Blocking
摘要：
作者姓名消歧（AND）算法从学术或类似数据库中的所有类似或相同出版物记录中识别唯一的作者实体记录。通常，使用聚类方法，该方法需要计算每个可能的记录对之间的相似性。然而，对的总数随着作者数据库的大小呈二次方增长，使得这种聚类难以处理数百万条记录。对此的一种补救措施是减少成对相似性计算的数量的分块函数。在这里，我们介绍了一种新的学习阻塞方案的方法，通过使用合取范式（CNF）的析取范式（DNF）。我们在PubMed作者记录中证明，与使用DNF的先前方法相比，CNF阻塞减少了更多的对，同时保持了高的对完整性，计算时间显着减少。因此，学术数据中的这些概念可以用CNF更好地表示。此外，我们还展示了如何确保该方法产生不相交的块，以便其余的AND算法可以很容易地被替换。我们的CNF拦截在整个PubMed数据库的8000万作者提及上进行了测试，在10分钟内有效地删除了82.17%的所有作者记录对。
英文摘要：
An author name disambiguation (AND) algorithm identifies a unique author entity record from all similar or same publication records in scholarly or similar databases. Typically, a clustering method is used that requires calculation of similarities between each possible record pair. However, the total number of pairs grows quadratically with the size of the author database making such clustering difficult for millions of records. One remedy for this is a blocking function that reduces the number of pairwise similarity calculations. Here, we introduce a new way of learning blocking schemes by using a conjunctive normal form (CNF) in contrast to the disjunctive normal form (DNF). We demonstrate on PubMed author records that CNF blocking reduces more pairs while preserving high pairs completeness compared to the previous methods that use a DNF with the computation time significantly reduced. Thus, these concepts in scholarly data can be better represented with CNFs. Moreover, we also show how to ensure that the method produces disjoint blocks so that the rest of the AND algorithm can be easily paralleled. Our CNF blocking tested on the entire PubMed database of 80 million author mentions efficiently removes 82.17% of all author record pairs in 10 minutes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
