%0 Journal Article %J Proceedings of DUC %D 2007 %T Multiple alternative sentence compressions for automatic text summarization %A Madnani,N. %A Zajic, David %A Dorr, Bonnie J %A Ayan,N.F. %A Jimmy Lin %X We perform multi-document summariza-tion by generating compressed versions of source sentences as summary candi- dates and using weighted features of these candidates to construct summaries. We combine a parse-and-trim approach with a novel technique for producing multiple alternative compressions for source sen- tences. In addition, we use a novel method for tuning the feature weights that maxi- mizes the change in the ROUGE-2 score (∆ROUGE) between the already existing summary state and the new state that re- sults from the addition of the candidate under consideration. We also describe ex- periments using a new paraphrase-based feature for redundancy checking. Finally, we present the results of our DUC2007 submissions and some ideas for future work. %B Proceedings of DUC %8 2007/// %G eng