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

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.

• Type: Journal
• Year: 2007
• Where: IPM
• Authors: David M. Zajic, Bonnie J. Dorr, Jimmy J. Lin, Richard M. Schwartz
• Keywords: IPM 2007, Multi-document Summarization, Sentence Compression, Sentence Compression Techniques