DBkWik: A consolidated knowledge graph from thousands of Wikis

DOI:	https://doi.org/10.1109/ICBK.2018.00011
URL:	https://ieeexplore.ieee.org/document/8588770
Additional URL:	http://data.dws.informatik.uni-mannheim.de/dbkwik/...
Document Type:	Conference or workshop publication
Year of publication:	2018
Book title:	9th IEEE International Conference on Big Knowledge, ICBK 2018, Singapore, November 17-18, 2018 : proceedings
Page range:	17-24
Conference title:	ICBK 2018
Location of the conference venue:	Singapore, Singapore
Date of the conference:	17.-18.11.2018
Publisher:	Wu, Xindong
Place of publication:	Piscataway, NJ [u.a.]
Publishing house:	IEEE Computer Society
ISBN:	978-1-5386-9124-3 , 978-1-5386-9126-7 , 978-1-5386-9125-0
Publication language:	English
Institution:	School of Business Informatics and Mathematics > Data Science (Paulheim 2018-)
Subject:	004 Computer science, internet
Abstract:	Popular knowledge graphs such as DBpedia and YAGO are built from Wikipedia, and therefore similar in coverage. In contrast, Wikifarms like Fandom contain Wikis for specific topics, which are often complementary to the information contained in Wikipedia, and thus DBpedia and YAGO. Extracting these Wikis with the DBpedia extraction framework is possible, but results in many isolated knowledge graphs. In this paper, we show how to create one consolidated knowledge graph, called DBkWik, from thousands of Wikis. We perform entity resolution and schema matching, and show that the resulting large-scale knowledge graph is complementary to DBpedia.