Towards Enriching Linked Open Data via Open InformationExtraction

First International Workshop on Knowledge Discovery and Data Mining Meets Linked Open Data

Antonis Koukourikos1 ; 2 ; Vangelis Karkaletsis2 ; George Vouros1

Others  :  http://ceur-ws.org/Vol-868/paper5.pdf
PID  :  43546

来源: CEUR

【 摘 要 】

The descriptions of various entities on Linked Data repositories are subject to constant renewals and modifications, with respect to both the descriptions of concepts and relations and en- tities realizing their instantiations. Thus, the underlying ontologies have to be updated accordinglyin order to reflect these changes. This paper presents a system for examining the possibilities ofdiscovering new relations and updating/verifying existing ones for entities described in Linked Da- ta repositories by using Open Information Extraction techniques. These are applied to web content.The process aims to the enrichment of the examined datasets and the expansion of the ontologieswith newly-discovered concepts and relations. Towards this target, the paper discusses the intrica- cies, pitfalls and challenges present.