From Meaningful Orderings in the Web of Data to Multi-level Pattern Structures

Quentin Brabant 1 Miguel Couceiro 1 Amedeo Napoli 1 Justine Reynaud 1
1 ORPAILLEUR - Knowledge representation, reasonning
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : We define a pattern structure whose objects are elements of a supporting ontology. In this framework, descriptions constitute trees, made of triples subject-predicate-object, and for which we provide a meaningful similarity operator. The specificity of the descriptions depends on a hy-perparameter corresponding to their depth. This formalism is compatible with ontologies formulated in the language of RDF and RDFS and aims to set up a framework based on pattern structures for knowledge discovery in the web of data.
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01544123
Contributor : Quentin Brabant <>
Submitted on : Wednesday, June 21, 2017 - 1:46:27 PM
Last modification on : Tuesday, December 18, 2018 - 4:38:02 PM
Long-term archiving on : Saturday, December 16, 2017 - 7:21:58 AM

File

ismis-jet-3.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01544123, version 1

Citation

Quentin Brabant, Miguel Couceiro, Amedeo Napoli, Justine Reynaud. From Meaningful Orderings in the Web of Data to Multi-level Pattern Structures. International Symposium on Methodologies for Intelligent Systems, Jun 2017, Warsaw, Poland. pp.622-631. ⟨hal-01544123⟩

Share

Metrics

Record views

288

Files downloads

174