Rough Set based Aggregate Rank Measure & its Application to Supervised Multi Document Summarization.

摘要: Most problems in Machine Learning cater to classification and the objects of universe are classified a relevant class. Ranking per decision class is challenging problem. We this paper propose novel Rough Set based membership called Rank Measure solve It shall be utilized for ranking elements particular differs from Pawlak function which gives an equivalent characterization approximations. becomes paramount look beyond traditional approach computing memberships while handling inconsistent, erroneous missing data that typically present real world problems. This led us aggregate Measure. The contribution three fold. Firstly, it proposes measure numerical within objects. Secondly, establish properties membership. Thirdly, we apply concept problem supervised Multi Document Summarization wherein first important sentences determined using various learning techniques post processed proposed measure. results proved have significant improvement accuracy.