Collaborative Datasets Retrieval for Interlinking on Web of Data

Abstract

Dataset interlinking is a great important problem in Linked Data. We consider this problem from the perspective of information retrieval in this paper, thus propose a learning to rank based framework, which combines various similarity measures to retrieve the relevant datasets for a given dataset. Specifically, inspired by the idea of collaborative filtering, an effective similarity measure called collaborative similarity is proposed. Experimental results show that the collaborative similarity measure is effective for dataset interlinking, and the learning to rank based framework can significantly increase the performance.