Combining attribute grammars and ontologies for extracting information from PDF documents

In this paper is presented a novel approach for semantic extraction of information from PDF documents that because of their unstructured nature pose many issues. The approach is founded on the idea of self-describing ontologies in which objects and classes can be equipped by a set of rules named descriptors. These rules are productions of an attribute context free grammar. They represent patterns that allow to automatically recognize and extract ontology objects contained in PDF documents also when information is arranged in tabular form. This way a self-describing ontology expresses the semantics of the information to extract and the rules that, in turn, populate itself. The approach is sketched by means of a running example.