×

Argument based machine learning. (English) Zbl 1168.68481

Summary: We present a novel approach to machine learning, called ABML (argumentation based ML). This approach combines machine learning from examples with concepts from the field of argumentation. The idea is to provide expert’s arguments, or reasons, for some of the learning examples. We require that the theory induced from the examples explains the examples in terms of the given reasons. Thus arguments constrain the combinatorial search among possible hypotheses, and also direct the search towards hypotheses that are more comprehensible in the light of expert’s background knowledge. In this paper we realize the idea of ABML as rule learning. We implement ABCN2, an argument-based extension of the CN2 rule learning algorithm, conduct experiments and analyze its performance in comparison with the original CN2 algorithm.

MSC:

68T05 Learning and adaptive systems in artificial intelligence
68T27 Logic in artificial intelligence

Software:

UCI-ml
PDFBibTeX XMLCite
Full Text: DOI Link

References:

[1] Ashley, K. D.; Rissland, E. L., Law, learning and representation, Artificial Intelligence, 150, 17-58 (2003) · Zbl 1082.68597
[2] I. Bratko, M. Možina, Argumentation and machine learning, in: Deliverable 2.1 for the ASPIC project, 2004; I. Bratko, M. Možina, Argumentation and machine learning, in: Deliverable 2.1 for the ASPIC project, 2004
[3] S. Brüninghaus, K.D. Ashley, Predicting the outcome of case-based legal arguments, in: G. Sartor (Ed.), Proceedings of the 9th International Conference on Artificial Intelligence and Law (ICAIL), Edinburgh, United Kingdom, June 2003, pp. 233-242; S. Brüninghaus, K.D. Ashley, Predicting the outcome of case-based legal arguments, in: G. Sartor (Ed.), Proceedings of the 9th International Conference on Artificial Intelligence and Law (ICAIL), Edinburgh, United Kingdom, June 2003, pp. 233-242
[4] B. Cestnik, Estimating probabilities: A crucial task in machine learning, in: Proceedings of the Ninth European Conference on Artificial Intelligence, 1990, pp. 147-149; B. Cestnik, Estimating probabilities: A crucial task in machine learning, in: Proceedings of the Ninth European Conference on Artificial Intelligence, 1990, pp. 147-149
[5] P. Clark, Representing arguments as background knowledge for constraining generalisation, in: D. Sleeman (Ed.), Third European Working Session on Learning, October 1988; P. Clark, Representing arguments as background knowledge for constraining generalisation, in: D. Sleeman (Ed.), Third European Working Session on Learning, October 1988
[6] P. Clark, R. Boswell, Rule induction with CN2: Some recent improvements, in: Machine Learning—Proceedings of the Fifth European Conference (EWSL-91), Berlin, 1991, pp. 151-163; P. Clark, R. Boswell, Rule induction with CN2: Some recent improvements, in: Machine Learning—Proceedings of the Fifth European Conference (EWSL-91), Berlin, 1991, pp. 151-163
[7] Clark, P.; Niblett, T., The CN2 induction algorithm, Machine Learning Journal, 4, 3, 261-283 (1989)
[8] J. Demšar, B. Zupan, Orange: From experimental machine learning to interactive data mining, White Paper, http://www.ailab.si/orange; J. Demšar, B. Zupan, Orange: From experimental machine learning to interactive data mining, White Paper, http://www.ailab.si/orange
[9] Domingos, P., The role of Occam’s razor in knowledge discovery, Data Mining and Knowledge Discovery, 3, 4, 409-425 (1999)
[10] Džeroski, S.; Cestnik, B.; Petrovski, I., Using the m-estimate in rule induction, CIT J. Comput. Inf. Technol., 1, 37-46 (1993)
[11] S.A. Gomez, C.I. Chesnevar, Integrating defeasible argumentation and machine learning techniques, Technical report, Universidad Nacional del Sur, 2004; S.A. Gomez, C.I. Chesnevar, Integrating defeasible argumentation and machine learning techniques, Technical report, Universidad Nacional del Sur, 2004
[12] Gomez, S. A.; Chesnevar, C. I., Integrating defeasible argumentation with fuzzy art neural networks for pattern classification, Journal of Computer Science and Technology, 4, 1, 45-51 (April 2004)
[13] Jensen, D. D.; Cohen, P. R., Multiple comparisons in induction algorithms, Machine Learning, 38, 3, 309-338 (March 2000)
[14] Možina, M.; Demšar, J.; Žabkar, J.; Bratko, I., Why is rule learning optimistic and how to correct it, (Fuernkranz, J.; Scheffer, T.; Spiliopoulou, M., Proceedings of 17th European Conference on Machine Learning (ECML 2006). Proceedings of 17th European Conference on Machine Learning (ECML 2006), Berlin (2006), Springer-Verlag), 330-340
[15] Možina, M.; Žabkar, J.; Bench-Capon, T.; Bratko, I., Argument based machine learning applied to law, Artificial Intelligence and Law, 13, 1, 53-73 (2006)
[16] Možina, M.; Žabkar, J.; Bratko, I., Argument based rule learning, (Proceedings of 17th European Conference on Artificial Intelligence (ECAI 2006). Proceedings of 17th European Conference on Artificial Intelligence (ECAI 2006), Riva Del Garda, Italy (2006), IOS Press) · Zbl 1168.68481
[17] M. Možina, J. Žabkar, I. Bratko, D3.4: Implementation of and experiments with abml and mlba, ASPIC Deliverable D3.4, 2006; M. Možina, J. Žabkar, I. Bratko, D3.4: Implementation of and experiments with abml and mlba, ASPIC Deliverable D3.4, 2006
[18] P.M. Murphy, D.W. Aha, UCI repository of machine learning databases, http://www.ics.uci.edu/ mlearn/mlrepository.html; P.M. Murphy, D.W. Aha, UCI repository of machine learning databases, http://www.ics.uci.edu/ mlearn/mlrepository.html
[19] Pazzani, M.; Mani, S.; Shankle, W. R., Beyond concise and colorful: Learning intelligible rules, (Third International Conference on Knowledge Discovery and Data Mining. Third International Conference on Knowledge Discovery and Data Mining, Newport Beach, CA (1997), AAAI Press), 235-238
[20] Pazzani, M. J., Influence of prior knowledge on concept acquisition: Experimental and computational results, Journal of Experimental Psychology: Learning, Memory and Cognition, 17, 416-432 (1991)
[21] Prakken, H.; Vreeswijk, G., Logics for defeasible argumentation, (Handbook of Philosophical Logic, vol. 4 (2002), Kluwer Academic Publishers: Kluwer Academic Publishers Dordrecht), 218-319 · Zbl 1003.03503
[22] Rousseauw, J.; du Plessis, J.; Benade, A.; Jordann, P.; Kotze, J.; Jooste, P.; Ferreira, J., Coronary risk factor screening in three rural communities, South African Medical Journal, 64, 430-436 (1983)
[23] J. Žabkar, M. Možina, J. Videčnik, I. Bratko, Argument based machine learning in a medical domain, in: E.P. Dunne, T.J.M. Bench-Capon (Eds.), Proceedings of Computational Models of Argument (COMMA), 2006, pp. 59-70; J. Žabkar, M. Možina, J. Videčnik, I. Bratko, Argument based machine learning in a medical domain, in: E.P. Dunne, T.J.M. Bench-Capon (Eds.), Proceedings of Computational Models of Argument (COMMA), 2006, pp. 59-70
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.