Multi-candidate reduction: Sentence compression as a tool for document summarization tasks |
| |
| Authors: | David Zajic Bonnie J Dorr Jimmy Lin Richard Schwartz |
| |
| Institution: | aUniversity of Maryland, College Park, MD 20742, United States;bBBN Technologies, 9861 Broken Land Parkway, Columbia, MD 21046, United States |
| |
| 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. |
| |
| Keywords: | Headline generation Summarization Parse-and-trim Hidden Markov model |
| 本文献已被 ScienceDirect 等数据库收录！ |
