A hierarchical naive Bayes mixture model for name disambiguation in author citations

Abstract

Because of name variations, an author may have multiple names and multiple authors may share the same name. Such name ambiguity affects the performance of document retrieval, web search, database integration, and may cause improper attribution to authors. This paper presents a hierarchical naive Bayes mixture model, an unsupervised learning approach, for name disambiguation in author citations. This method partitions a collection of citations 1 into clusters, with each cluster containing only citations authored by the same author, thus disambiguating authorship in citations to induce author name identities. Three types of citation features are used: co-author names, paper title words, and journal or proceeding title words. The approach is illustrated with 16 name datasets that are constructed based on the publication lists collected from author homepages and DBLP computer science bibliography.

Detecting referential inconsistencies in electronic CV datasets

“…They use a mix of techniques. While some use similarity functions [2,7,12,18,21,27,30], others use learning techniques [1,14,16,28,32,35], heuristics [17,19,20,24], classifiers [9,10,34] and clustering methods [11,31].…”

“…If no tuple is returned found, we attempt to retrieve the coauthor by the full name (lines 6-7), which is returned in case it is found (line 9). If there is no success and if the coauthor's name contains a period and/or a semicolon (which characterizes a citation name) (line 10), the heuristic tries to find the coauthor's CV by using the citation name (lines [11][12][13][14]. Since this query may retrieve several tuples, we use a similarity function to find the most similar coauthor in the database (lines 15-24).…”

Flexible and Efficient Distributed Resolution of Large Entities

“…We can apply data mining classification methods, for example Bayes methods [23,18], decision trees [31] or SVM [7,11]. Unsupervised learning methods such as latent Dirichlet allocation [3] or clustering methods can also be used, if there is no training data.…”

Author Name Disambiguation for Citations Using Topic and Web Correlation

“…To resolve this problem, some relational information is used to facilitate the disambiguation task. For example, Han et al [12] try to improve disambiguation accuracy by clustering title words and venue words with similar concepts. Song et al [13] introduce the relationships between authors and topics in citations to improve the disambiguation accuracy by extracting the wordbased relationships for each topic.…”