Multiple alternative sentence compressions for automatic text summarization

TitleMultiple alternative sentence compressions for automatic text summarization
Publication TypeJournal Articles
Year of Publication2007
AuthorsMadnani N, Zajic D, Dorr BJ, Ayan NF, Jimmy Lin
JournalProceedings of DUC
Date Published2007///
Abstract

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.