论文信息 - A Sentence-Trimming Approach to Multi-Document Summarization

A Sentence-Trimming Approach to Multi-Document Summarization

We implemented an initial application of a sentence-trimming approach (Trimmer) to the problem of multi-document summarization in the MSE2005 and DUC2005 tasks. Sentence trimming was incorporated into a feature-based summarization system, called MultiDocument Trimmer (MDT), by using sentence trimming as both a preprocessing stage and a feature for sentence ranking. We demonstrate that we were able to port Trimmer easily to this new problem. Although the direct impact of sentence trimming was minimal compared to other features used in the system, the interaction of the other features resulted in trimmed sentences accounting for nearly half of the selected summary sentences.

Richard M. Schwartz | Christof Monz | Bonnie J. Dorr | Jimmy Lin | David Zajic

[1] David Evans,et al. Columbia University at DUC 2004 , 2004 .

[2] Dragomir R. Radev,et al. Centroid-based summarization of multiple documents , 2004, Inf. Process. Manag..

[3] Dragomir R. Radev,et al. The University of Michigan at DUC 2004 , 2004 .

[4] Martin F. Porter,et al. An algorithm for suffix stripping , 1997, Program.

[5] Richard M. Schwartz,et al. BBN/UMD at DUC-2004: Topiary , 2004 .

[6] Richard M. Schwartz,et al. Hedge Trimmer: A Parse-and-Trim Approach to Headline Generation , 2003, HLT-NAACL 2003.

[7] Ani Nenkova,et al. Evaluating Content Selection in Summarization: The Pyramid Method , 2004, NAACL.

[8] Eduard H. Hovy,et al. Automatic Evaluation of Summaries Using N-gram Co-occurrence Statistics , 2003, NAACL.

[9] Jaime Carbonell,et al. Multi-Document Summarization By Sentence Extraction , 2000 .