Reconciling Information in DBpedia through a Question Answering System - Inria - Institut national de recherche en sciences et technologies du numérique
Poster Communications Year : 2014

Reconciling Information in DBpedia through a Question Answering System

Abstract

Results obtained querying language-speci c DBpedia chap- ters SPARQL endpoints for the same query can be related by several het- erogenous relations, or contain an inconsistent set of information about the same topic. To overcome this issue in question answering systems over language-speci c DBpedia chapters, we propose the RADAR frame- work for information reconciliation. Starting from a categorization of the possible relations among the resulting instances, such framework: (i) classi es such relations, (ii) reconciles the obtained information using argumentation theory, (iii) ranks the alternative results depending on the con dence of the source in case of inconsistencies, and (iv) explains the reasons underlying the proposed ranking.
No file

Dates and versions

hal-01076616 , version 1 (22-10-2014)

Identifiers

  • HAL Id : hal-01076616 , version 1

Cite

Elena Cabrio, Alessio Palmero Aprosio, Serena Villata. Reconciling Information in DBpedia through a Question Answering System. ISWC 2014 : 13th International Semantic Web Conference, Oct 2014, Riva del Garda, Italy. , 1272, 2014, Proceedings of the ISWC 2014 Posters & Demonstrations Track a track within the 13th International Semantic Web Conference (ISWC 2014). ⟨hal-01076616⟩
415 View
0 Download

Share

More