Wikipedia’s infoboxes contain rich structured information of various entities, which have been exploited by the DBpedia project to generate large-scale Linked Data datasets. Among all the infobox attributes, those attributes which have hyperlinked values identifying semantic relations between entities are the most important for creating links between DBpedia’s instances. However, quite a few of the hyperlinks in infoboxes have not been annotated by editors, which causes lots of missing relations between entities in Wikipedia. The speaker proposes an approach for automatically discovering the missing entity links in Wikipedia’s infoboxes, so that the missing semantic relations between entities can be established.
Keywords: Link prediction, Machine Learning, DBpedia, Semantic relationships
Author: Wang, Zhichun
Date created: 2013-11-28 05:00:00.000
Time required: P20M
Educational use: instruction
Educational audience: professional
Interactivity type: expositive