GK: Implementing Full First Order Default Logic for Commonsense Reasoning (System Description)
Tanel Tammet, Dirk Draheim, Priit Järv · Lecture notes in computer science · 2022
Abstract Our goal is to develop a logic-based component for hybrid – machine learning plus logic – commonsense question answering systems. The paper presents an implementation GK of default logic for handling rules with exceptions in unrestricted first order knowledge bases. GK is built on top of our existing automated reasoning system with confidence calculation capabilities. To overcome the problem of undecidability of checking potential exceptions, GK performs delayed recursive checks with diminishing time limits. These are combined with the taxonomy-based priorities for defaults and numerical confidences.