Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
515115 | Information Processing & Management | 2007 | 22 Pages |
Abstract
This article examines the application of two single-document sentence compression techniques to the problem of multi-document summarization—a “parse-and-trim” approach and a statistical noisy-channel approach. We introduce the multi-candidate reduction (MCR) framework for multi-document summarization, in which many compressed candidates are generated for each source sentence. These candidates are then selected for inclusion in the final summary based on a combination of static and dynamic features. Evaluations demonstrate that sentence compression is a valuable component of a larger multi-document summarization framework.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Science Applications
Authors
David Zajic, Bonnie J. Dorr, Jimmy Lin, Richard Schwartz,