Natural Logic Knowledge Bases and Their Graph Form

This paper describes how knowledge bases can be represented in and reasoned with in natural logic. Natural logic is a regimented fragment of natural language possessing a well-defined logical semantics. As such, natural logic may be considered an attractive alternative among the various knowledge representation logics such as description logics. Our version of natural logic expands formal ontologies with affirmative propositions expressing a variety of relationships between concepts. It comprises (nested) restrictive relative clauses and prepositional phrases and, as a new construct, adverbial prepositional phrases. The natural logic knowledge base is to be used for deductive query answering applying inference rules. This is facilitated by introduction of Datalog as an embedding meta-logic. The inference rules are stated in Datalog and act directly on the natural logic formulations. The knowledge base propositions are decomposed into a graph form enabling path finding between concepts. The examples in the paper are derived from text source life-science descriptions.