Multi-candidate reduction: Sentence compression as a tool for document summarization tasks

TitleMulti-candidate reduction: Sentence compression as a tool for document summarization tasks
Publication TypeJournal Articles
Year of Publication2007
AuthorsZajic D, Dorr BJ, Jimmy Lin, Schwartz R
JournalInformation Processing & Management
Volume43
Issue6
Pagination1549 - 1570
Date Published2007/11//
ISBN Number0306-4573
KeywordsHeadline generation, Hidden Markov model, Parse-and-trim, Summarization
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.

URLhttp://www.sciencedirect.com/science/article/pii/S0306457307000295
DOI10.1016/j.ipm.2007.01.016