To aim is to rank the objects from the output of a classifier. The ranking is performed per category of the data. Classifier can be a machine learning or AI based classifier. The model is evaluated on Multi Document Text Summarization standard datasets using well known performance metrics.
This article is about my own research paper titled “Rough Set based Aggregate Rank Measure & its Application to Supervised Multi Document Summarization”
Most problems in Machine Learning cater to classification and the objects of universe are classified to a relevant class. Ranking of classified objects of universe per decision class is a challenging problem. The following are key points.
1. In this paper a novel Rough Set based membership called Rank Measure is proposed to solve to this problem. It shall be utilized for ranking the elements to a particular class.
2. It differs from Pawlak Rough Set based membership function which gives an equivalent characterization of the Rough Set based approximations.
3. It becomes paramount to look beyond the traditional approach of computing memberships while handling inconsistent, erroneous and missing data that is typically present in real world problems. This led us to propose the aggregate Rank Measure.
The contribution of the paper is three fold.
a. It proposes a Rough Set based measure to be utilized for numerical characterization of within class ranking of objects.
b. It proposes and establish the mathematical properties of Rank Measure and aggregate Rank Measure based membership.
c. The concept of membership and aggregate ranking is applied to the problem of supervised Multi Document Summarization wherein first the important class of sentences are determined using various supervised learning techniques and are post processed using the proposed ranking measure.
The results proved to have significant improvement in accuracy.
This is a novel and interesting area of research. I am working more on this area.