Learning Probabilistic Description Logics: A Framework and Algorithms

Luna, José Eduardo Ochoa; Revoredo, Kate; Cozman, Fábio Gagliardi

doi:10.1007/978-3-642-25324-9_3

Cited by 10 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [8] the authors used an extension of ALC, called crALC that adopts an interpretation-based semantics. crALC allows statistical axioms of the form P (C|D) = α, which means that for any element x in D, the probability that it is in C given that is in D is α, and of the form P (R) = β, which means that for each couple of elements x and y in D, the probability that x is linked to y by the role R is β. Axioms of the form P (C|D) = α are equivalent to DISPONTE axioms of the form α :: x C D, while axioms of the form P (R) = β have no equivalent in DISPONTE but can be introduced in principle.…”

Section: Related Workmentioning

confidence: 99%

“…The algorithm of [8] learns parameters and structure of crALC knowledge bases. It starts from positive and negative examples for a single concept and learns a probabilistic definition for the concept.…”

Section: Related Workmentioning

confidence: 99%

“…Various authors have studied the use of probabilistic DLs and many proposals have been presented for allowing Description Logics(DLs) to represent uncertainty [8,13,7].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Parameter Learning for Probabilistic Ontologies

Riguzzi

Bellodi

Lamma

et al. 2013

Web Reasoning and Rule Systems

View full text Add to dashboard Cite

Recently, the problem of representing uncertainty in Description Logics (DLs) has received an increasing attention. In probabilistic DLs, axioms contain numeric parameters that are often difficult to specify or to tune for a human. In this paper we present an approach for learning and tuning the parameters of probabilistic ontologies from data. The resulting algorithm, called EDGE, %for Em over bDds for description loGics paramEter learning, is targeted to DLs following the DISPONTE approach, that applies the distribution semantics to DLs

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Parameter Learning for Probabilistic Ontologies

Riguzzi

Bellodi

Lamma

et al. 2013

Web Reasoning and Rule Systems

View full text Add to dashboard Cite

show abstract

“…A probabilistic ontology was then learned using algorithms in the literature [20,24]. This ontology is comprised by 24 probabilistic inclusions and 17 concept definitions.…”

Section: Ann)mentioning

confidence: 99%

Link prediction using a probabilistic description logic

2013

Self Cite

View full text Add to dashboard Cite

Due to the growing interest in social networks, link prediction has received significant attention. Link prediction is mostly based on graph-based features, with some recent approaches focusing on domain semantics. We propose algorithms for link prediction that use a probabilistic ontology to enhance the analysis of the domain and the unavoidable uncertainty in the task (the ontology is specified in the probabilistic description logic crALC). The scalability of the approach is investigated, through a combination of semantic assumptions and graph-based features. We evaluate empirically our proposal, and compare it with standard solutions in the literature.

show abstract

“…A probabilistic ontology was then learned using algorithms in the literature [Ochoa-Luna et al 2011, Revoredo et al 2010. This ontology is comprised by 24 probabilistic inclusions and 17 concept definitions.…”

Section: Scenario Descriptionmentioning

confidence: 99%

Organizing Institutions

2013

Nuclear Physics B - Proceedings Supplements

View full text Add to dashboard Cite

Ontology is a cross-disciplinary field concerning the study of concepts and theories that support the building of shared conceptualizations of specific domains. In recent years, there has been a growing interest in the application of ontologies to solve modeling and classification problems in diverse areas such as Computer Science, Information Science, Philosophy, Artificial Intelligence, Linguistic, Knowledge Management and many others. The Seminar on Ontology Research in Brazil, ONTOBRAS, foresees an opportunity and scientific environment in which researchers and practitioners from Information Sciences and Computer Science can discuss the theories, methodologies, languages, tools and experiences related to ontologies development and application. Particularly, this Seminar Six Edition took place in an Information Science school, as the result of an effort of the ontologies research community in exchanging experiences and in integrating Information Science and Computer Science initiatives.

show abstract

Learning Probabilistic Description Logics: A Framework and Algorithms

Cited by 10 publications

References 17 publications

Parameter Learning for Probabilistic Ontologies

Parameter Learning for Probabilistic Ontologies

Link prediction using a probabilistic description logic

Organizing Institutions

Contact Info

Product

Resources

About