In this paper we present SPREFQL, an extension of the SPARQL language that allows appending a "PREFER" clause that expresses 'soft' preferences over the query results obtained by the main body of the query. The extension does not add expressivity and any SPREFQL query can be transformed to an equivalent standard SPARQL query. However, clearly separating preferences from the 'hard' patterns and filters in the "WHERE" clause gives queries where the intention of the client is more cleanly expressed, an advantage for both human readability and machine optimization. In the paper we formally define the syntax and the semantics of the extension and we also provide empirical evidence that optimizations specific to SPREFQL improve run-time efficiency by comparison to the usually applied optimizations on the equivalent standard SPARQL query.This general preference relation is restricted into intrinsic preference formulas that do not rely on external information to compare two objects:
Abstract-We describe an Inductive Logic Programming (ILP) approach to learning descriptions in Description Logics (DL) under uncertainty. The approach is based on implementing many-valued DL proofs as propositionalizations of the elementary DL constructs and then providing this implementation as background predicates for ILP. The proposed methodology is tested on a many-valued variation of eastbound-trains and Iris, two well known and studied Machine Learning datasets. I. INTRODUCTIONDescription logics (DL) are a family of logics that has found many applications in conceptual and semantic modelling, and is one of the key technologies behind semantic web applications.Fuzzy and, in general, many-valued extensions of DL semantics have given significant boost to their importance in both related fields: semantic conceptualization gains a means of expressing the uncertainty that is inherent in real-world modelling problems and uncertainty inference gains access to the vast conceptualization effort that has been carried out in the context of the semantic web.Despite, however, the rapid progress in inference methods for many-valued DL, there has been very limited success in applying machine learning methodologies to this family of logics, and especially to its more expressive members (such as those covering OWL and OWL 2) that are routinely used in web intelligence applications.In this paper we first introduce the machine learning discipline of Inductive Logic Programming and then discuss previous work on applying ILP to learning DL (Section II). These approaches tend to propose adaptation of ILP algorithms so that they cover DL, but are restricted to the less expressive members of the DL family. Instead, we investigate a novel approach whereby we re-formulate DL inference within the ILP paradigm, effectively mapping our problem to an equivalent problem within the domain of application of ILP (Section III). We evaluate our approach by applying an unadapted ILP system to a DL learning task under this mapping (Section IV), and close the paper by drawing conclusions and outlining future research directions (Section V).
General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.• Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal Take down policyIf you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.