AutoSummENG and MeMoG in Evaluating Guided Summaries.

Abstract

Within this article, we present the application of the AutoSummENG and MeMoG methods within the TAC 2011 AESOP challenge. Both evaluation methods are based on n-gram graphs. The experiments indicate that both methods offer very high performance in different aspects of evaluation, without the need of deep analysis or preprocessing. The results also imply some interesting open problems and point to further directions of study, related to negative examples of good summaries.