Knowledge Graph Curation and Reasoning using the Example of the Scholarly Domain

Talk by Sahar Vahdati

Location: APB 3027
Start: 30. January 2020 at 1:00 pm
End: 30. January 2020 at 2:30 pm
Research group: Knowledge-Based Systems
Event series: KBS Seminar
iCal

Knowledge graphs allow organisations and enterprises to integrate their internal and external heterogeneous sources of information into a unified form and enable analytics and discovery of unknown knowledge. To exploit the information encoded in knowledge graphs, analysis of the graph structure as well as the semantics of the represented relations, is required. I will show this using the scholarly domain as an example. The heterogeneity of scholarly artifacts and their metadata spread over different Web data sources serve as a great use case platform for data analytics and reasoning methods. In this talk, I will first have a look into major challenges of this domain using KG creation and curation leveraging semantic Web technologies. I will further showcase the application of Knowledge Graph Embedding models for link prediction scenarios of this domain.