On c-learnability in description logics

Authors:
Ali Rezaei Divroodi;Quang-Thuy Ha;Linh Anh Nguyen;Hung Son Nguyen
Affiliations:
Faculty of Mathematics, Informatics and Mechanics, University of Warsaw, Warsaw, Poland;Faculty of Information Technology, College of Technology, Vietnam National University, Hanoi, Vietnam;Faculty of Mathematics, Informatics and Mechanics, University of Warsaw, Warsaw, Poland;Faculty of Mathematics, Informatics and Mechanics, University of Warsaw, Warsaw, Poland
Venue:
ICCCI'12 Proceedings of the 4th international conference on Computational Collective Intelligence: technologies and applications - Volume Part I
Year:
2012

Citing 8
Cited 0

A theory of the learnable

Communications of the ACM
A Refinement Operator for Description Logics

ILP '00 Proceedings of the 10th International Conference on Inductive Logic Programming
An algorithm based on counterfactuals for concept learning in the Semantic Web

Applied Intelligence
DL-FOIL Concept Learning in Description Logics

ILP '08 Proceedings of the 18th international conference on Inductive Logic Programming
An Efficient Tableau Prover using Global Caching for the Description Logic ALC

Fundamenta Informaticae - Concurrency Specification and Programming (CS&P)
Concept learning in description logics using refinement operators

Machine Learning
A bisimulation-based method of concept learning for knowledge bases in description logics

Proceedings of the Third Symposium on Information and Communication Technology
Concept Learning for Description Logic-Based Information Systems

KSE '12 Proceedings of the 2012 Fourth International Conference on Knowledge and Systems Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

We prove that any concept in any description logic that extends $\mathcal{ALC}$ with some features amongst I (inverse), Qk (quantified number restrictions with numbers bounded by a constant k), Self (local reflexivity of a role) can be learnt if the training information system is good enough. That is, there exists a learning algorithm such that, for every concept C of those logics, there exists a training information system consistent with C such that applying the learning algorithm to the system results in a concept equivalent to C.