German National Socialist Injustice on the Semantic Web: from archival records to a knowledge graph

Abstract: Archival repositories contain vast amounts of historical data within unstructured textual documents, posing significant challenges for extracting coherent insights. This presentation, in the Doctoral Consortium of the 23rd Internation Semantic Web Conference, presents ongoing work towards an optimised workflow for constructing a knowledge graph from millions of archival records related to the “Wiedergutmachung” process in Germany. These records, documenting compensation and restitution efforts following World War II, offer insights into the aftermath of the National Socialist regime. The proposed workflow involves converting document images to machine-readable formats, ontology design, information extraction, and entity linking. Leveraging both traditional methods and transform