Imprecision and vagueness are inherent characteristics of human knowledge and their role in knowledge engineering and knowledge-based systems development has been extensively examined in the literature. IKARUS (Imprecise Knowledge Acquisition Representation and Use) is a knowledge management framework that provides a comprehensive set of methods and tools for capturing, modeling, retrieving and managing vague knowledge in enterprise and organizational settings. Its development is based on the combination of techniques and methods from the areas of Case Based Reasoning, Ontologies and Fuzzy Logic.
IKARUS-Onto is a novel methodology for effectively developing reusable and shareable fuzzy ontologies from existing crisp ones. The methodology provides concrete steps and guidelines for i) correctly identifying vague knowledge within a domain (e.g. by not mixing vagueness with other notions such as uncertainty or ambiguity) and ii) modelling this knowledge by means of fuzzy ontology elements in an explicit and as much as possible accurate way.
IKARUS-CBR is a novel Knowledge Intensive Case Based Reasoning framework that may handle and exploit vague knowledge through the effective integration of Fuzzy Ontologies in the CBR paradigm. The approach it follows differs from other Fuzzy CBR approaches in that it uses ontologies as the “vehicle” for the introduction of fuzzy semantics to CBR. The integration of Fuzzy Ontologies in CBR is performed in the framework in two levels, the first having to do with the representation of vague knowledge itself and the second with the latter’s exploitation for case retrieval. In particular, the framework supports the representation of vague case-specific and domain-specific knowledge through a comprehensive fuzzy ontology framework while the retrieval of cases is enabled by a highly customizable fuzzy semantic similarity framework.
IKARUS-Learner is a semi-automatic framework for acquiring and maintaining fuzzy ontological knowledge from user interactions. So far, two types of interactions have been considered i) user-system ones in dialogue systems and ii) user-user ones in enterprise social platforms.
P. Alexopoulos, J. Pavlopoulos (2014), “A Vague Sense Classifier for Detecting Vague Definitions in Ontologies”. In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2014), Gothenburg, Sweden, 2014. [BibTex, PDF]
P. Alexopoulos, J.M. Gómez-Pérez (2013) “Interactive Acquisition of Fuzzy Ontological Knowledge in Dialogue Systems”. In Proceedings of the 7th international conference on Knowledge capture (K-CAP ’13). Banff, Canada.
P. Alexopoulos, J. Pavlopoulos, Ph. Mylonas (2012), “Learning Vague Knowledge From Socially Generated Content in an Enterprise Framework”, Proceedings of the 1st Mining Humanistic Data Workshop (MHDW 2012), Halkidiki, Greece, September 27-30, 2012.
P. Alexopoulos, M. Wallace, K. Kafentzis, D. Askounis (2011), “IKARUS-Onto: A Methodology to Develop Fuzzy Ontologies from Crisp Ones” , Knowledge and Information Systems, Volume 32, Issue 3, Page 667-695.
P. Alexopoulos, M. Wallace, K. Kafentzis, D. Askounis (2010), “Utilizing Imprecise Knowledge in Ontology-based CBR Systems through Fuzzy Algebra”, International Journal of Fuzzy Systems, Vol. 12, No. 1, March 2010.
P. Alexopoulos, M. Wallace, K. Kafentzis, D. Askounis (2010), “A Semantic Architecture for Knowledge Intensive CBR through Fuzzy Ontologies”, 15th UK Workshop on Case Based Reasoning, December 14th 2010, Cambridge, UK.
P. Alexopoulos, M. Wallace, K. Kafentzis, D. Askounis (2009) “Towards Effective Knowledge Management Through Fuzzy Semantics” , The Third International Multi-Conference on Computing in the Global Information Technology 2009, Cannes, France, August 23-29.
P. Alexopoulos, M. Wallace, K. Kafentzis (2008), “A Fuzzy Ontology Framework for Customized Assessment of Semantic Similarity”, 3rd International Workshop on Semantic Media and Adaptation (SMAP 2008), Prague, Czech Republic, December 15-16.