Reasoning with Large Scale Ontologies in Fuzzy pD* Using MapReduce

This is the first work to investigate how MapReduce can be applied to solve the scalability issue of fuzzy reasoning in OWL, and the running time of the system is comparable with that of WebPIE, the state-of-the-art inference engine for scalable reasoning in pD* semantics.

Abstract

The MapReduce framework has proved to be very efficient for data-intensive tasks. Earlier work has successfully applied MapReduce for large scale RDFS/OWL reasoning. In this paper, we move a step forward by considering scalable reasoning on semantic data under fuzzy pD* semantics (i.e., an extension of OWL pD* semantics with fuzzy vagueness). To the best of our knowledge, this is the first work to investigate how MapReduce can be applied to solve the scalability issue of fuzzy reasoning in OWL. While most of the optimizations considered by the existing MapReduce framework for pD* semantics are also applicable for fuzzy pD* semantics, unique challenges arise when we handle the fuzzy information. Key challenges are identified with solution proposed for each of these challenges. Furthermore, a prototype system is implemented for the evaluation purpose. The experimental results show that the running time of our system is comparable with that of WebPIE, the state-of-the-art inference engine for scalable reasoning in pD* semantics.