A Knowledge-based Representation for Cross-Language Document Retrieval and Categorization

Franco Salvador Marc, Rosso Paolo, Navigli Roberto

2014

A Knowledge-based Representation for Cross-Language Document Retrieval and Categorization

In this paper we propose a shift from the supervised to the knowledge-based paradigm and provide a document similarity measure which draws on BabelNet, a large multilingual knowledge resource. Our experiments show state-of-the-art results in cross-lingual document retrieval and categorization.