Pay-less entity consolidation

Abstract

Linked Data consists of billions of RDF triples from hundreds of different sources on the Web. The effective construction and maintenance of links between these sources largely depend on data integration solutions that scale to the large volume and heterogeneity of the Linked Data Web. In this context, a promising direction is the pay-as-you-go paradigm that advocates the use of user feedback for an interactive and incremental approach to data integration-to obtain a solution that continuously improves as the underlying system evolves. In this paper, we study pay-as-you-go data integration in the context of entity search. Compared with asking users to contribute to the result quality without to directly benefit from their effort, we show that users "pay less" when entity consolidation is inherently embedded in entity search. In this setting, users interact with the system for solving their tasks, and as a side-effect, contribute to the quality of the consolidation results. We propose an iterative clustering procedure to implement this concept of pay-less entity consolidation. We demonstrate its promising advantages over traditional solutions grounded on an extensive evaluation.