Preferences‚ Links‚ and Probabilities for Ranking Objects in Ontologies

<p>In previous work, we have introduced variable-strength conditional preferences for ranking objects in ontologies. In this paper, we continue this line of research. We propose a new ranking of objects, which integrates this user-defined preference ranking of objects with Google's import...

Full description

Bibliographic Details
Main Authors: Lukasiewicz, T, Schellhase, J
Format: Conference item
Published: CEUR−WS.org 2006
_version_ 1797060005404344320
author Lukasiewicz, T
Schellhase, J
author_facet Lukasiewicz, T
Schellhase, J
author_sort Lukasiewicz, T
collection OXFORD
description <p>In previous work, we have introduced variable-strength conditional preferences for ranking objects in ontologies. In this paper, we continue this line of research. We propose a new ranking of objects, which integrates this user-defined preference ranking of objects with Google's importance ranking (called <em>PageRank</em>) based on the link structure between the objects. We also propose to use probabilistic description logics based on Bayesian networks and the description logic <em>DL-Lite</em> to compute the ranking of incompletely specified objects.</p>
first_indexed 2024-03-06T20:11:40Z
format Conference item
id oxford-uuid:2ac5c64f-49d4-46c9-9f38-7efb532c4d30
institution University of Oxford
last_indexed 2024-03-06T20:11:40Z
publishDate 2006
publisher CEUR−WS.org
record_format dspace
spelling oxford-uuid:2ac5c64f-49d4-46c9-9f38-7efb532c4d302022-03-26T12:27:03ZPreferences‚ Links‚ and Probabilities for Ranking Objects in OntologiesConference itemhttp://purl.org/coar/resource_type/c_5794uuid:2ac5c64f-49d4-46c9-9f38-7efb532c4d30Department of Computer ScienceCEUR−WS.org2006Lukasiewicz, TSchellhase, J<p>In previous work, we have introduced variable-strength conditional preferences for ranking objects in ontologies. In this paper, we continue this line of research. We propose a new ranking of objects, which integrates this user-defined preference ranking of objects with Google's importance ranking (called <em>PageRank</em>) based on the link structure between the objects. We also propose to use probabilistic description logics based on Bayesian networks and the description logic <em>DL-Lite</em> to compute the ranking of incompletely specified objects.</p>
spellingShingle Lukasiewicz, T
Schellhase, J
Preferences‚ Links‚ and Probabilities for Ranking Objects in Ontologies
title Preferences‚ Links‚ and Probabilities for Ranking Objects in Ontologies
title_full Preferences‚ Links‚ and Probabilities for Ranking Objects in Ontologies
title_fullStr Preferences‚ Links‚ and Probabilities for Ranking Objects in Ontologies
title_full_unstemmed Preferences‚ Links‚ and Probabilities for Ranking Objects in Ontologies
title_short Preferences‚ Links‚ and Probabilities for Ranking Objects in Ontologies
title_sort preferences links and probabilities for ranking objects in ontologies
work_keys_str_mv AT lukasiewiczt preferenceslinksandprobabilitiesforrankingobjectsinontologies
AT schellhasej preferenceslinksandprobabilitiesforrankingobjectsinontologies