On the Power and Limitations of Examples for Description Logic Concepts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cate, Balder ten, Koudijs, Raoul, Ozaki, Ana
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915076131258368
author Cate, Balder ten
Koudijs, Raoul
Ozaki, Ana
author_facet Cate, Balder ten
Koudijs, Raoul
Ozaki, Ana
contents Labeled examples (i.e., positive and negative examples) are an attractive medium for communicating complex concepts. They are useful for deriving concept expressions (such as in concept learning, interactive concept specification, and concept refinement) as well as for illustrating concept expressions to a user or domain expert. We investigate the power of labeled examples for describing description-logic concepts. Specifically, we systematically study the existence and efficient computability of finite characterisations, i.e. finite sets of labeled examples that uniquely characterize a single concept, for a wide variety of description logics between EL and ALCQI, both without an ontology and in the presence of a DL-Lite ontology. Finite characterisations are relevant for debugging purposes, and their existence is a necessary condition for exact learnability with membership queries.
format Preprint
id arxiv_https___arxiv_org_abs_2412_17345
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On the Power and Limitations of Examples for Description Logic Concepts
Cate, Balder ten
Koudijs, Raoul
Ozaki, Ana
Logic in Computer Science
Machine Learning
F.4.1; I.2.6; I.2.4
Labeled examples (i.e., positive and negative examples) are an attractive medium for communicating complex concepts. They are useful for deriving concept expressions (such as in concept learning, interactive concept specification, and concept refinement) as well as for illustrating concept expressions to a user or domain expert. We investigate the power of labeled examples for describing description-logic concepts. Specifically, we systematically study the existence and efficient computability of finite characterisations, i.e. finite sets of labeled examples that uniquely characterize a single concept, for a wide variety of description logics between EL and ALCQI, both without an ontology and in the presence of a DL-Lite ontology. Finite characterisations are relevant for debugging purposes, and their existence is a necessary condition for exact learnability with membership queries.
title On the Power and Limitations of Examples for Description Logic Concepts
topic Logic in Computer Science
Machine Learning
F.4.1; I.2.6; I.2.4
url https://arxiv.org/abs/2412.17345