Using prior probabilities and density estimation for relational classification

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

9 Citations (Scopus)

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.
Original languageEnglish
Title of host publicationProceedings of the 8th International Conference on Inductive Logic Programming (ILP-98)
PublisherSpringer
Pages106-115
Volume1446
DOIs
Publication statusPublished - Jul 1998

Publication series

NameLecture Notes in Artificial Intelligence

Fingerprint

Dive into the research topics of 'Using prior probabilities and density estimation for relational classification'. Together they form a unique fingerprint.

Cite this