How Can Reasoner Performance of ABox Intensive Ontologies Be Predicted?

Isa Guclu, Carlos Bobed, Jeff Z. Pan, Martin J. Kollingbaum, Yuan-Fang Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Reasoner performance prediction of ontologies in OWL 2 language has been studied so far from different dimensions. One key aspect of these studies has been the prediction of how much time a particular task for a given ontology will consume. Several approaches have adopted different machine learning techniques to predict time consumption of ontologies already. However, these studies focused on capturing general aspects of the ontologies (i.e., mainly the complexity of their TBoxes), while paying little attention to ABox intensive ontologies. To address this issue, in this paper, we propose to improve the representativeness of ontology metrics by developing new metrics which focus on the ABox features of ontologies. Our experiments show that the proposed metrics contribute to overall prediction accuracy for all ontologies in general without causing side-effects.
Original languageEnglish
Title of host publicationSemantic Technology
EditorsYuan-Fang Li, Wei Hu, Jin Song Dong, Grigoris Antoniou, Zhe Wang, Jun Sun, Yang Liu
Place of PublicationCham
PublisherSpringer International Publishing
Pages3-14
Number of pages12
ISBN (Electronic)978-3-319-50112-3
ISBN (Print)978-3-319-50111-6
DOIs
Publication statusPublished - 27 Nov 2016
Event6th Joint International Semantic Technology Conference - , Singapore
Duration: 2 Nov 20164 Nov 2016
http://pat.sce.ntu.edu.sg/jist2016/

Publication series

NameLecture Notes in Computer Science
PublisherSpringer, Cham
Volume10055
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference6th Joint International Semantic Technology Conference
Abbreviated titleJIST 2016
CountrySingapore
Period2/11/164/11/16
Internet address

Keywords

  • Semantic web
  • Ontology reasoning
  • Prediction
  • Random forests
  • Knowledge graph
  • Practical reasoning

Fingerprint

Dive into the research topics of 'How Can Reasoner Performance of ABox Intensive Ontologies Be Predicted?'. Together they form a unique fingerprint.

Cite this