The University of Michigan in Novelty 2004

[摘要] This year we participated in the Novelty track. To find the relevant sentences, we combine sentence salience features that are inherited from text summarization domain with other heuristic features based on topic statements. We propose a novel method to extract the new sentences based on the graphbased ranking

[学科分类] 社会科学、人文和艺术（综合）