Black-box Testing of First-Order Logic Ontologies Using WordNet
share
A long-standing dream of Artificial Intelligence (AI) has pursued to enrich computer programs with commonsense knowledge enabling machines to reason about our world. This paper offers a new practical insight towards the automation of commonsense reasoning with first-order logic (FOL) ontologies. We propose a new black-box testing methodology of FOL SUMO-based ontologies by exploiting WordNet and its mapping into SUMO. Our proposal includes a method for the (semi-)automatic creation of a very large set of tests and a procedure for its automated evaluation by using automated theorem provers (ATPs). Applying our testing proposal, we are able to successfully evaluate a) the competency of several translations of SUMO into FOL and b) the performance of various automated ATPs. In addition, we are also able to evaluate the resulting set of tests according to different quality criteria.
READ FULL TEXT