Title: Learning the parameters of probabilistic logic programs from interpretations
Other Titles: See also ERRATUM
Authors: Gutmann, Bernd
Thon, Ingo
De Raedt, Luc
Issue Date: 2011
Publisher: Springer
Host Document: Machine Learning and Knowledge Discovery in Databases vol:6911 pages:581-596
Series Title: Lecture Notes in Computer Science
Conference: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) location:Athens, Greece date:5-9 September 2011
Article number: 489
Abstract: ProbLog is a recently introduced probabilistic extension of the logic programming language Prolog, in which facts can be annotated with the probability that they hold. The advantage of this probabilistic language is that it naturally expresses a generative process over interpretations using a declarative model. Interpretations are relational descriptions or possible worlds. This paper introduces a novel parameter estimation algorithm LFI-ProbLog for learning ProbLog programs from partial interpretations. The algorithm is essentially a Soft-EM algorithm. It constructs a propositional logic formula for each interpretation that is used to estimate the marginals of the probabilistic parameters. The LFI-ProbLog algorithm has been experimentally evaluated on a number of data sets that justifies the approach and shows its effectiveness.
Description: acceptance rate = 20%
ISBN: 978-3-642-23780-5
ISSN: 0302-9743
Publication status: published
KU Leuven publication type: IC
Appears in Collections:Informatics Section

Files in This Item:
File Description Status SizeFormat
gutmann_489.pdfMain article Accepted 379KbAdobe PDFView/Open
erratum.pdf Published 103KbAdobe PDFView/Open


All items in Lirias are protected by copyright, with all rights reserved.

© Web of science