N-GRAM GRAPHS: REPRESENTING DOCUMENTS AND DOCUMENT SETS IN SUMMARY SYSTEM EVALUATION
George Giannakopoulos, Vangelis Karkaletsis · 2009
Within this article, we present the application of the AutoSummENG method within the TAC 2009 AESOP challenge. We further offer an alternative to the original AutoSummENG method, which uses an additional operator of the n-gram graph framework to represent a set of documents with a single, merged graph. Both alternatives offer very good results in different aspects of the AESOP results evaluation. The original AutoSummENG method appears a very good linear estimator of Pyramid score and responsiveness, while the new Merged Model variation offers very good (non-linear) rank estimation performance when correlated to the responsiveness measure.