This year we took part in the genomic information retrieval and information extraction tasks, as well as the named page and topic distillation searches. In carrying out the last two tasks, we made use of link anchor information and document content in order to construct Web page representatives. This type of document representation uses multi-vectors to highlight the importance of both hyperlin...

This year we took part in the Arabic cross-language information retrieval track (for us limited to monolingual Arabic retrieval) and also in both named page and topic distillation searches. In the last two tasks, we made use of link anchor information and document content in order to construct Web page representatives. This document representation uses multi-vectors in order to highlight the im...