Linear Concept Approximation for Multilingual Document Recommendation

Vilmos Tibor Salamon, Tsegaye Misikir Tashu, Tomás Horváth

Abstract: In this paper, we proposed Linear Concept Approximation, a novel multilingual document representation approach for the task of multilingual document representation and recommendation. The main idea is in creating representations by using mappings to align monolingual representation spaces using linear concept approximation, that in turn will enhance the quality of content-based Multilingual Document Recommendation Systems. The experimental results on JRC-Acquis have shown that our proposed approach outperformed traditional methods on the task of multilingual document recommendation.