Contribution to the Classification of Web of Data based on Formal Concept Analysis

Justine Reynaud 1 Yannick Toussaint 1 Amedeo Napoli 1
1 ORPAILLEUR - Knowledge representation, reasonning
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : During the last decade, the web has taken a huge importance in everyday life, and has become what is commonly called a web of data. The available resources can be used by human agents but also by software agents, as it is the case for very large ontologies such as YAGO or resources such as DBpedia. These particular datasets can be linked together for constituting the Linked Open Data (LOD) cloud, where basic data are expressed as (subject, predicate, object) triples. One issue of main interest is knowledge discovery within LOD, which can help information retrieval and knowledge engineering. Formal concept analysis (FCA), which is a mathematical theory allowing classification and data analysis, was already used to classify LOD elements. In this research work, we are interested in analyzing the different approaches (extensions) based on FCA for knowledge discovery in the web of data. One objective is to study the efficiency and the applicability of the existing approaches and to propose some improvements.
Document type :
Conference papers
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.inria.fr/hal-01420466
Contributor : Justine Reynaud <>
Submitted on : Tuesday, December 20, 2016 - 4:15:25 PM
Last modification on : Tuesday, December 18, 2018 - 4:38:02 PM
Long-term archiving on : Tuesday, March 21, 2017 - 2:10:35 PM

File

FCA4AI_2016_paper_17.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01420466, version 1

Collections

Citation

Justine Reynaud, Yannick Toussaint, Amedeo Napoli. Contribution to the Classification of Web of Data based on Formal Concept Analysis. What can FCA do for Artificial Intelligence (FCA4AI) (ECAI 2016), Aug 2016, La Haye, Netherlands. ⟨hal-01420466⟩

Share

Metrics

Record views

355

Files downloads

132