An algorithm for the induction Of defeasible logic theories from databases

Johnston, Benjamin and Governatori, Guido (2003). An algorithm for the induction Of defeasible logic theories from databases. In: Klaus-Dieter Schewe and Xiaofang Zhou, Database technologies: Proceedings of the Fourteenth Australasian Database Conference. Fourteenth Australasian Database Conference, Adelaide, Australia, (75-83). 4-7 February, 2003.

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
adc03.pdf adc03.pdf application/pdf 154.37KB 321
Author Johnston, Benjamin
Governatori, Guido
Title of paper An algorithm for the induction Of defeasible logic theories from databases
Conference Paper Type Fully Published Paper
Conference name Fourteenth Australasian Database Conference    (ERA 2010 Rank B)
Conference location Adelaide, Australia
Conference dates 4-7 February, 2003
Proceedings title Database technologies: Proceedings of the Fourteenth Australasian Database Conference
Editor Klaus-Dieter Schewe
Xiaofang Zhou
Place published Sydney, Australia
Publisher Australian Computer Society
Publication date 2003
Volume number 17
ISBN 090992595X
Start page 75
End page 83
Total pages 10
Language eng
Abstract/Summary Defeasible logic is a non-monotonic logic with applications in rule-based domains such as law. To ease the development and improve the accuracy of expert systems based on defeasible logic, it is desirable to automatically induce a theory of the logic from a training set of precedent data. Empirical evidence suggests that minimal theories that describe the training set tend to be more faithful representations of reality. We show via transformation from the hitting set problem that this global minimization problem is intractable, belonging to the class of NP optimisation problems. Given the inherent difficulty of finding the optimal solution, we instead use heuristics and demonstrate that a best-first, greedy, branch and bound algorithm can be used to find good theories in short time. This approach displays significant improvements in both accuracy and theory size as compared to recent work in the area that post-processed the output of an Aprori association rule-mining algorithm, with comparable execution times.
Subjects 280100 Information Systems
230102 Number Theory And Field Theory
280400 Computation Theory and Mathematics
280213 Other Artificial Intelligence
0806 Information Systems
Keyword Data mining
Defeasible logic
Normative reasoning
Artificial intelligence and law
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status Unknown
Additional Notes Copyright (c) 2003, Australian Computer Society, Inc. This paper appeared at Fourteenth Australasian Database Conference, Adelaide. Conferences in Research and Practice in Information Technology, Vol. 17. K.D. Schewe and X. Zhou, Eds. Reproduction for academic, not-for profit purposes permitted provided this text is included.

 
Versions
Version Filter Type
Citation counts: Google Scholar Search Google Scholar
Access Statistics: 216 Abstract Views, 321 File Downloads  -  Detailed Statistics
Created: Mon, 21 Mar 2005, 10:00:00 EST by Guido Governatori on behalf of School of Information Technol and Elec Engineering