On C-Learnability in Description Logics
نویسندگان
چکیده
We prove that any concept in any description logic that extendsALC with some features amongst I (inverse),Qk (quantified number restrictions with numbers bounded by a constant k), Self (local reflexivity of a role) can be learnt if the training information system is good enough. That is, there exists a learning algorithm such that, for every concept C of those logics, there exists a training information system consistent with C such that applying the learning algorithm to the system results in a concept equivalent to C.
منابع مشابه
From \ Principles of Knowledge Representation and Reasoning : Proceedings of the Fourth International Conference " Learning the Classic Description Logic : Theoretical and Experimental
We present a series of theoretical and experimental results on the learnability of description logics. We rst extend previous formal learnability results on simple description logics to C-Classic, a description logic expressive enough to be practically useful. We then experimentally evaluate two extensions of a learning algorithm suggested by the formal analysis. The rst extension learns C-Clas...
متن کاملLearnability of the Classic Knowledge Representation Language
Much of the work in inductive learning considers languages that represent hypotheses using some restricted form of propositional logic; an important research problem is extending propo-sitional learning algorithms to use more expressive rst-order representations. Further, it is desirable for these algorithms to have solid theoretical foundations, so that their behavior is reliable and predictab...
متن کاملExact Learning of TBoxes in EL and DL-Lite
We study polynomial time learning of description logic TBoxes in Angluin et al.’s framework of exact learning via queries. We admit entailment queries (“is a given subsumption entailed by the target TBox?”) and equivalence queries (“is a given TBox equivalent to the target TBox?”), assuming that the signature and logic of the target TBox are known. We present three main results: (1) TBoxes form...
متن کاملOntology Learning from Interpretations in Lightweight Description Logics
Data-driven elicitation of ontologies from structured data is a well-recognized knowledge acquisition bottleneck. The development of efficient techniques for (semi-)automating this task is therefore practically vital_yet, hindered by the lack of robust theoretical foundations. In this paper, we study the problem of learning Description Logic TBoxes from interpretations, which naturally translat...
متن کاملCan doxastic agents learn? On the temporal structure of learning Extended Abstract
Formal learning theory constitutes an attempt to describe and explain the phenomenon of language acquisition. The considerations in this domain are also applicable in philosophy of science, where it can be interpreted as a theory of empirical inquiry. The main issue within this theory is to determine which classes of languages are learnable and how learnability is affected by e.g. restricting t...
متن کامل