Generating automatically labeled data for author name disambiguation: an iterative clustering method
Generating automatically labeled data for author name disambiguation: an iterative clustering method
复制标题
DOI：
10.1007/s11192-018-2968-3
复制
发表时间：
2018-11
期刊：
影响因子：
3.9
通讯作者：
Jinseok Kim;J. Kim;Jason Owen-Smith
中科院分区：
文献类型：
--
作者：
Jinseok Kim;J. Kim;Jason Owen-Smith
为了训练用于监督作者姓名消歧的算法，许多研究都依赖于手工标记的真实数据，这些数据生成起来非常费力。本文表明，标记数据可以自动生成的信息功能，如电子邮件地址，合著者的名字，引用的参考文献，可从出版记录。为此，使用外部权威数据库来决定用于匹配每个特征上的名称实例的高精度规则。然后，在目标歧义数据中选择名称实例进行基于规则的成对匹配过程。接下来，通过通用实体解析算法将它们合并到聚类中。聚类过程在其他特征上重复，直到进一步合并是不可能的。在228 K个作者姓名实例中的26 K个实例上进行测试，这种迭代聚类产生了精确标记的数据，成对F1 = 0.99。标记的数据代表人口数据的名称种族和共同消除歧义的名称组大小分布。此外，在标记数据上进行训练，机器学习算法消除了测试数据中24 K个名称的歧义，性能为pairwiseF 1 = 0.90-0.92。讨论了应用这种方法解决大规模学术数据中作者姓名歧义的几个挑战。
To train algorithms for supervised author name disambiguation, many studies have relied on hand-labeled truth data that are very laborious to generate. This paper shows that labeled data can be automatically generated using information features such as email address, coauthor names, and cited references that are available from publication records. For this purpose, high-precision rules for matching name instances on each feature are decided using an external-authority database. Then, selected name instances in target ambiguous data go through the process of pairwise matching based on the rules. Next, they are merged into clusters by a generic entity resolution algorithm. The clustering procedure is repeated over other features until further merging is impossible. Tested on 26 K instances out of the population of 228 K author name instances, this iterative clustering produced accurately labeled data with pairwiseF1 = 0.99. The labeled data represented the population data in terms of name ethnicity and co-disambiguating name group size distributions. In addition, trained on the labeled data, machine learning algorithms disambiguated 24 K names in test data with performance of pairwiseF1 = 0.90–0.92. Several challenges are discussed for applying this method to resolving author name ambiguity in large-scale scholarly data.