... 1: Results of the test of identifying the manual summariser287Figure 1: Illustration of some of the restrictions on Q, Kis reliable, or the evaluation outcome may changeby adding, for instance, ... con-trastive summary, the number of fragments of the reference summary which are also in the contrastive summary, in relation to the size of the contrastive summary.DocSim: The number of documents used ... probabilisticframework, QARLA, for the evaluation of text summarisation systems. The in-put of the framework is a set of man-ual (reference) summaries, a set of base-line (automatic) summaries and a set of similarity...