Information retrieval is regarded as pivotal to empower lay users to access the Web of Data.
Over the past years, it achieved momentum with a large number of approaches design for different scenarios being developed such as entity retrieval, question answering, and entity linking.
This work copes with the problem of entity retrieval over RDF knowledge graphs using keyword factual queries.
It discloses an approach that incorporates keyword graph structure dependencies through a conditional spread activation.
Experimental evaluation on standard benchmarks demonstrates that the proposed method can improve the performance of current state-of-the-art entity retrieval approaches significantly.
CACAO-Semantics2019.pdf
Msc.
AKSW, Universität Leipzig
www.aksw.org
Edgard is a Linked Data Expert at eccenca GmbH and guest researcher at INFAI and HTWK with broad experience in software engineering, project management, and designing innovative solutions. His main topics of interest rely on Semantic Web and Natural Language Processing over large knowledge graphs with a focus on information retrieval and distributed data management.
