| Status: Past project Project Description:
Dealing with uncertainty is crucial in ontology engineering tasks such
as domain modeling, ontology reasoning, and concept mapping between
ontologies. The Bayes OWL project addresses this problem by exploring
how uncertainty can be modeled in ontologies using Bayesian networks
(BN). Our approach involves extending OWL to allow additional
probabilistic markups for attaching probability information. Having
done so, we can directly convert a probabilistically annotated OWL
ontology into a BN structure using a set of structural translation
rules. The conditional probability tables (CPTs) of this BN can then
be constructed using a new method based on iterative proportional
fitting procedure (IPFP). Such translated BNs can be used to support
more accurate ontology reasoning under uncertainty as Bayesian
inferences. Start Date: September 2003 End Date: December 2006 Principal Investigator:
Yun Peng Students:
Zhongli Ding
Rong Pan
There are 4 associated publications:
 Click here for a full list...
There is 1 associated resource:  Hide the list... 1. Uncertainty in Ontology Mapping: A Bayesian Perspective, Presentation.
Research Areas:
Knowledge Representation and Reasoning
Semantic Web
| 
