Sixth TUC Meeting: SPIMBENCH for the Semantic Publishing Domain by Nina Saveta (Forth)
The second presentation during last LDBC's 6th TUC Meeting that took place in Barcelona was called SPIMBENCH: A Scalable, Schema-Aware, Instance Matching Benchmark for the Semantic Publishing Domain and presented by Tzanina Saveta from FORTH.
The SPIMBENCH is a benchmark that allows comparing & assessing Instance Matching systems and algorithms. Instance Matching allows automatically recognizing multiple mentions of the same entity across or within sources. The SPIMBENCH is based on the Semantic Publishing Benchmark of LDBC (more information here), it allows for a synthetic benchmark for the Semantic Publishing Domain, is valued-based, stucture-based and with semantic-aware transformations. It also is deterministic and allows scalable data generation in the order of billion of triples. All of it while weighted gold standard research.
Watch Tzanina Saveta presenting all the details of the SPIMBENCH:
You can also read more information about the SPB on this website or read our former blog posts here.
Stay tuned for the rest of presentations!