Taking into account Inter-sentence Similarity for Update Summarization

Maâli Mnasri, Gaël de Chalendar, Olivier Ferret

Abstract:

Following Gillick and Favre (2009), a lot
of work about extractive summarization
has modeled this task by associating two
contrary constraints: one aims at maxi-
mizing the coverage of the summary with
respect to its information content while
the other represents its size limit. In this
context, the notion of redundancy is only
implicitly taken into account. In this ar-
ticle, we extend the framework defined
by Gillick and Favre (2009) by examin-
ing how and to what extent integrating se-
mantic sentence similarity into an update
summarization system can improve its re-
sults. We show more precisely the impact
of this strategy through evaluations per-
formed on DUC 2007 and TAC 2008 and
2009 datasets.