On the Power and Limitations of Examples for Description Logic Concepts

Autor:	Cate, Balder ten, Koudijs, Raoul, Ozaki, Ana
Rok vydání:	2024
Předmět:	Computer Science - Logic in Computer Science Computer Science - Machine Learning F.4.1 I.2.6 I.2.4
Zdroj:	Proceedings of the 33rd International Joint Conference on Artificial Intelligence (2024), pp.3567-3575
Druh dokumentu:	Working Paper
DOI:	10.24963/ijcai.2024/395
Popis:	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. Comment: Published in the Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2412.17345 Zobrazit plný text záznamu View this record from Arxiv