Acosta, Juan C.; Marcial Romero, J. R.; Hernández Camacho, J. (2012). Implementing a Knowledge Bases Debugger. Artificial Intelligence (MICAI), 2012 11th Mexican International Conference on. Escuela Superior de Huejutla. UAEH. México. ISBN: En trámite.
Knowledge representation is an important topic in common-sense reasoning and Artificial Intelligence, and one of the earliest techniques to represent it is by means of knowledge bases encoded into logic clauses. Encoding knowledge, however, is prone to typos and other kinds of consistency mistakes, which may yield incorrect results or even internal contradictions with conflicting information from other parts of the same code. In order to overcome such situations, we propose a logic-programming system to debug knowledge bases. The system has a strong theoretical framework on knowledge representation and reasoning, and a suggested on-line prototype where one can test logic programs. Such logic programs may have, of course, conflicting information and the system shall prompt the user where the possible source of conflict is. Besides, the system can be employed to identify conflicts of the knowledge base itself and upcoming new information, it can also be used to locate the source of conflict from a given inherently inconsistent static knowledge base. This paper describes an implementation of a declarative version of the system that has been characterised to debug knowledge bases in a semantical formalism. Some of the key components of such implementation are existing solvers, so this paper focuses on how to use them and why they work, towards an implemented a fully-fledged system.