JenTab: Matching Tabular Data to Knowledge Graphs

Abstract: A lot of knowledge is traditionally captured within tables using free text entries. Due to the inherent issues of free text like typos and inconsistent naming, integrating that knowledge with other data is seriously hindered. Using semantic techniques to annotate the individual parts of a table can alleviate this task and support access to this vast reservoir of knowledge. However, converting legacy tables into a semantically annotated representation is a non-trivial challenge due to the scarcity of context and the ambiguity and noisiness of the available content. In this paper, we report on our system “JenTab” developed in the context of the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching (SemTab2020). “JenTab” tries to create as much as possible of semantic annotations for table parts. Then, iteratively reduce these candidates by levering different levels of information to reach the most specific solution.