Towards an Approach based on Knowledge Graph Refinement for Tabular Data to Knowledge Graph Matching
This paper presents our contribution to the Accuracy Track of Semantic Web Challenge on Tabular Data to Knowledge Graph Matching (SemTab). This contribution consists of the proposition of an approach based on knowledge graph refinement for tabular data annotation. Internal methods were used to predict the links between cells in the table and external methods were used to predict missing entities and relations. This approach was applied to the annotation of HardTables and ToughTables using DBpedia and Wikidata; and GitTables and BiodivTab using DBpedia and Schema.org. During Round 3 of the competition, we were ranked third and second position respectively for the annotation of GitTables and BiodivTab.
PDF