BayesOWL: Uncertainty Modeling in Semantic Web Ontologies

Abstract

It is always essential but difficult to capture incomplete, partial or uncertain knowledge when using ontologies to conceptualize an application domain or to achieve semantic interoperability among heterogeneous systems. This chapter presents an on-going research on developing a framework which augments and supplements the semantic web ontology language OWL 5 for representing and reasoning with uncertainty based on Bayesian networks (BN) [26], and its application in ontology mapping. This framework, named BayesOWL, has gone through several iterations since its conception in 2003 [8,9]. BayesOWL provides a set of rules and procedures for direct translation of an OWL ontology into a BN directed acyclic graph (DAG), it also provides a method based on iterative proportional fitting procedure (IPFP) [19,7,6,34,2,4] that incorporates available probability constraints when constructing the conditional probability tables (CPTs) of the BN. The translated BN, which preserves the semantics of the original ontology and is consistent with all the given probability constraints, can support ontology reasoning, both within and across ontologies as Bayesian inferences. At the present time, BayesOWL is restricted to translating only OWL-DL concept taxonomies into BNs, we are actively working on extending the framework to OWL ontologies with property restrictions.If ontologies are translated to BNs, then concept mapping between ontologies can be accomplished by evidential reasoning across the translated BNs. This approach to ontology mapping is seen to be advantageous to many existing methods in handling uncertainty in the mapping. Our preliminary work on this issue is presented at the end of this chapter.This chapter is organized as follows: Sect. 1 provides a brief introduction to semantic web 6 and discusses uncertainty in semantic web ontologies; Sect. 2 5

Semantic Aware Bayesian Network Model for Actionable Knowledge Discovery in Linked Data

“…BayesOWL consists of a set of construction rules, which convert ontology files into BN directed acyclic graphs (DAG), which preserve the semantics of the original ontology file [11,12]. Likewise, the model proposed in this paper follows the same rules to convert the given LD file into BN DAG.…”

Managing uncertainty and vagueness in description logics for the Semantic Web

“…In [18,19], Ding et al propose a probabilistic generalization of OWL, called BayesOWL, which is based on standard Bayesian networks. BayesOWL provides a set of rules and procedures for the direct translation of an OWL ontology into a Bayesian network, and it also provides a method for incorporating available probability constraints when constructing the Bayesian network.…”

“…The generated Bayesian network, which preserves the semantics of the original ontology and which is consistent with all the given probability constraints, supports ontology reasoning, both within and across ontologies, as Bayesian inferences. In [104,19], Ding et al also describe an application of the BayesOWL approach in ontology mapping.…”

Uncertainty modeling process for semantic technology

“…In recognition of this need, the past decade has seen a significant increase in formalisms that integrate uncertainty representation into ontology languages. This has given birth to several new languages such as: PR-OWL (Costa, 2005;Costa, Laskey & Laskey, 2005;Costa, Laskey & Laskey, 2008;Carvalho, 2011;Carvalho, Laskey & Costa, 2013), OntoBayes (Yang & Calmet, 2005), BayesOWL (Ding, Peng & Pan, 2006), P-CLASSIC (Koller, Levy & Pfeffer, 1997) and probabilistic extensions of SHIF (D) and SHOIN(D) (Lukasiewicz, 2008).…”