PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Summarization system evaluation variations based on n-gram graphs
George Giannakopoulos and Vangelis Karkaletsis
In: TAC 2010, 15-16 November 2010, MD, U.S.A..

Abstract

Within this article, we present the application of the AutoSummENG method within the TAC 2010 AESOP challenge. We further present two novel evaluation methods based on n-gram graphs. The first method is called Merged Model Graph (MeMoG) and it uses the n-gram graph framework to represent a set of documents with a single, ``centroid'' graph, offering state-of-the-art performance. The second method is called Hierarchical Proximity Graph (HPG) evaluation and it uses a hierarchy of graphs to represent texts, aiming to represent different granularity levels under a unified view. The experiments indicate that both novel methods offer very promising performance in different aspects of evaluation, improving on AutoSummENG scores.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
ID Code:7596
Deposited By:George Giannakopoulos
Deposited On:17 March 2011