Unit:
Κατεύθυνση / ειδίκευση Διαχείριση Πληροφορίας και Δεδομένων (ΔΕΔ)Πληροφορική
Supervisors info:
Μανόλης Κουμπαράκης, Καθηγητής, Τμήμα Πληροφορικής και Τηλεπικοινωνιών, Εθνικό και Καποδιστριακό Πανεπιστήμιο Αθηνών
Original Title:
Extending the YAGO Knowledge Graph with Geospatial Knowledge
Translated title:
Extending the YAGO Knowledge Graph with Geospatial Knowledge
Summary:
YAGO is one of the largest knowledge bases that provide their data as Linked Open Data.
Spatial information, in the form of points, was introduced in YAGO2, the second version of
YAGO. In this work we present an extension of YAGO with qualitative geospatial inform-
ation (i.e., polygons and lines), which was extracted from multiple sources. We studied
datasets that are provided from crowdsourced projects as well as from official sources of
several countries. It is important to point out that we do not introduce duplicate information
in the knowledge graph of YAGO, by creating entities that already exist. Hence, at first,
we try to match entities of YAGO with the entities of the data sources that we used. Our
results show that our methodology produced matches with very high precision. This work
is concluded with a demonstration of the extended knowledge graph.
Main subject category:
Technology - Computer science
Keywords:
linked open data, semantic web, knowledge graphs, knowledge bases