Black-box Testing of First-Order Logic Ontologies Using WordNet
This work addresses the challenge of systematically testing commonsense reasoning systems for AI researchers and ontology developers, representing an incremental improvement in evaluation methodology.
The paper tackles the problem of evaluating commonsense reasoning in first-order logic ontologies by developing a black-box testing methodology that uses WordNet to automatically generate and evaluate competency questions. The approach successfully assessed multiple SUMO translations and automated theorem provers, providing a comprehensive analysis of current FOL SUMO-based ontologies.
Artificial Intelligence aims to provide computer programs with commonsense knowledge to reason about our world. This paper offers a new practical approach towards automated 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 benchmark of competency questions and a procedure for its automated evaluation by using automated theorem provers (ATPs). Applying different quality criteria, our testing proposal enables a successful evaluation of a) the competency of several translations of SUMO into FOL and b) the performance of various automated ATPs. Finally, we also provide a fine-grained and complete analysis of the commonsense reasoning competency of current FOL SUMO-based ontologies.