@article {13831, title = {Multi-candidate reduction: Sentence compression as a tool for document summarization tasks}, journal = {Information Processing \& Management}, volume = {43}, year = {2007}, month = {2007/11//}, pages = {1549 - 1570}, abstract = {This article examines the application of two single-document sentence compression techniques to the problem of multi-document summarization{\textemdash}a {\textquotedblleft}parse-and-trim{\textquotedblright} 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, Hidden Markov model, Parse-and-trim, Summarization}, isbn = {0306-4573}, doi = {10.1016/j.ipm.2007.01.016}, url = {http://www.sciencedirect.com/science/article/pii/S0306457307000295}, author = {Zajic, David and Dorr, Bonnie J and Jimmy Lin and Schwartz,Richard} }