Using Prior Probabilities and Density
Estimation for Relational Classification

James Cussens

Department of Computer Science
University of York
Heslington, York Y010 5DD, UK
Tel: +44 1904 434732
Fax: +44 1904 432767
jc@cs.york.ac.uk




Abstract. A Bayesian method for incorporating probabilistic background
knowledge into ILP is presented. Positive only learning is extended to
allow density estimation. Estimated densities and defined prior are combined 
in Bayes theorem to perform relational classification. An initial
application of the technique is made to part-of-speech (POS) tagging. A
novel use of Gibbs sampling for POS tagging is given.
References

1.	Henrik Bostrm. Predicate invention and learning from positive examples only. In
Proceedings of the 10th European Conference on Machine Learning (ECML-98).
Springer, 1998.
2.	Wray Buntine. Learning classification trees. In D.J. Hand, editor, Artificial Intelligence 
Frontiers in Statistics: AI and Statistics III, chapter 15, pages 182201.
Chapman & Hall, London, 1993.
3.	J. Cussens. Bayesian Inductive Logic Programming with explicit probabilistic bias.
Technical Report PRG-TR-24-96, Oxford University Computing Laboratory, 1996.
4.	James Cussens. Part-of-speech tagging using Progol. In Inductive Logic Programming: 
Proceedings of the 7th International Workshop (ILP-97). LNAI 1297, pages
93108. Springer, 1997.
5.	Luc Dehaspe. Maximum entropy modeling with clausal constraints, In Inductive 
Logic Programming: Proceedings of the 7th International Workshop (ILP-97).
LNAI 1207, pages 109124. Springer, 1997.
6.	Joseph Y. Halpern. An analysis of first-order logics of probability. Artificial Intelligence, 
46:311350, 1990.
7.	D. Michie, D.J. Spiegeihalter, and C.G. Taylor. Machine Learning, Neural and
Statistical Classification. Ellis Horwood, Hemel Hempstead, 1994.
8.	S. Muggleton. Learning from positive data. In S. Muggleton, editor, Inductive 
Logic Programming: Proceedings of the 6th International Workshop (ILP-96).
LNAI 1314, pages 358376. Springer, 1996.
9.	Raymond Ng and V.S. Subrahmanian. Probabilistic logic programming. Information 
and Computation, 101(2):150201, 1992.
10.	Uros Pompe and Igor Kononenko. Probabilistic first-order classification. In Inductive 
Logic Programming: Proceedings of the 7th International Workshop (ILP-97),
pages 235243, 1997.
11.	A.F.M. Smith and G.O. Roberts. Bayesian computation via the Gibbs sampler
and related Markov chain Monte Carlo methods. Journal of the Royal Statistical
Society B, 55(1):323, 1993.
12.	A. Srinivasan. Sampling methods for the analysis of large datasets with ILP. Technical 
Report PRG-TR-27-97, Oxford University Computing Laboratory, Oxford,
1997.
13.	A. Srinivasan and R.D. King. Feature construction with inductive logic programming: 
A study of quantitative predictions of biological activity aided by structural
attributes. In S. Muggleton, editor, Inductive Logic Programming: Proceedings of
the 6th International Workshop (ILP-96). LNAI 1314, pages 89104. Springer,
1996.
