Reconciling Information in DBpedia through a Question Answering System

Results obtained querying language-specific DBpedia chapters SPARQL endpoints for the same query can be related by several heterogenous relations, or contain an inconsistent set of information about the same topic. To overcome this issue in question answering systems over language-specific DBpedia chapters, we propose the RADAR framework for information reconciliation. Starting from a categorization of the possible relations among the resulting instances, such framework: (i) classifies such relations, (ii) reconciles the obtained information using argumentation theory, (iii) ranks the alternative results depending on the confidence of the source in case of inconsistencies, and (iv) explains the reasons underlying the proposed ranking.