... Shane Bergsma, Sittichai Jiampojamarn and Grzegorz KondrakDepartment of Computing ScienceUniversity of AlbertaEdmonton, AB, T6G 2E8, Canada{qdou,bergsma,sj,kondrak}@cs.ualberta.caAbstractCorrect ... successful insimilar settings (learning with thousands of sparsefeatures) for both ranking and classification tasks, and because an efficient implementation is avail-able (Joachims, 1999).At test time ... constraints generated by Equation 1are called rank constraints. They are created sep-arately for every (sj, tj) training pair. Essen-tially, each training pair is matched with a setof automatically-created...