Affiliations: Université de Lyon, F-42023, Saint-Etienne, France | CNRS, UMR5516, Laboratoire Hubert Curien, F-42000, Saint-Etienne, France | Université de Saint-Etienne, Jean Monnet, F-42000, Saint-Etienne, France. E-mails: christophe.gravier@univ-st-etienne.fr, julien.subercaze@univ-st-etienne.fr | École Nationale Supérieure des Mines, FAYOL-ENSMSE, LSTI, F-42023 Saint-Étienne, France. E-mail: antoine.zimmermann@emse.fr
Abstract: In Semantic Web applications, reasoning engines that are data intensive commonly materialise inferences to speed up processing at query time. However, in evolving systems, such as smart environments, semantic-based context aware systems (SCAS) [6] or social software with user-generated data, knowledge does not grow monotonically: newer facts may contradict older ones, knowledge may be deprecated, discarded or updated such that knowledge must sometimes be retracted. We are describing a technique to retract explicit and inferred statements, when some information becomes obsolete, as well as retracting any statement that would lead to get back the removed explicit statements. This technique is based on OWL justifications and is triggered whenever a knowledge base becomes inconsistent, such that the system stays in a consistent state all the time, in spite of uncontrolled evolution. We prove termination and correctness of the algorithm, and describe the implementation and evaluation of the proposal.
