WorldKG Project (2019 - 2023)
Motivation
Knowledge graphs provide rich semantic representations of real-world entities and their relations. Whereas popular general-purpose knowledge graphs such as Wikidata and DBpedia contain selected geographic entities, their coverage of geographic information is limited. An essential source of openly available geographic information on the Web is OpenStreetMap (OSM) [1]. In contrast to knowledge graphs, OSM lacks a clear semantic representation of the rich geographic information it contains. Generation of semantic representations of OSM entities and their interlinking with knowledge graphs are inherently challenging due to the large, heterogeneous, ambiguous, and flat OSM schema and the annotation sparsity.
Project Results
As a result of the WorldKG project, we have developed methods for knowledge graph completion and to establish links between OSM and knowledge graphs at the entity and schema levels. In particular, we create the OSM2KG approach that is aimed at interlinking the representations of entities between OSM and knowledge graphs. We present a novel NCA algorithm to link the OSM tags that provide entity-type information to the corresponding knowledge graph classes. As a result, we semantically enrich geospatial information in OSM and make this information available in WorldKG - a novel geographic knowledge graph. The results of the WorldKG project demonstrate the application of semantic technologies to geospatial data.
The WorldKG project is funded by The German Research Foundation (DFG) under "WorldKG" (424985896), 2019-2023.
[1] OpenStreetMap is a trademark of the OpenStreetMap Foundation, and is used with their permission. This project is not endorsed by or affiliated with the OpenStreetMap Foundation.
Contact
Prof. Dr. Elena Demidova (DSIS Group)
Mail: elena.demidova@cs.uni-bonn.de
Dr. Alishiba Dsouza
Mail: dsouza@cs.uni-bonn.de