Semantically Conceptualizing and Annotating Tables

Enabling a system to automatically conceptualize and anno- tate a human-readable table is one way to create interesting semantic- web content. But exactly "how?" is not clear. With conceptualization and annotation in mind, we investigate a semantic-enrichment procedure as a way to turn syntactically observed table layout into semantically coher- ent ontological concepts, relationships, and constraints. Our semantic- enrichment procedure shows how to make use of auxiliary world knowl- edge to construct rich ontological structures and to populate these onto- logical structures with instance data. The system uses auxiliary knowl- edge (1) to recognize concepts and which data values belong to which concepts, (2) to discover relationships among concepts and which data- value combinations represent relationship instances, and (3) to discover constraints over the concepts and relationships that the data values and data-value combinations should satisfy. Experimental evaluations indi- cate that the automatic conceptualization and annotation processes per- form well, yielding F-measures of 90% for concept recognition, 77% for relationship discovery, and 90% for constraint discovery in web tables selected from the geopolitical domain.