Summarization Through Submodularity and Dispersion
Anirban Dasgupta, Ravi Kumar and Sujith Ravi
The 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013)
Sofia, Bulgaria, August 4-9, 2013
We propose a new optimization framework for summarization by generalizing the submodular framework of (Lin and Bilmes, 2011). In our framework the desiderata for summarization is expressed as a sum of a submodular function and a non-submodular function, which we call dispersion; the latter uses intersentence dissimilarities in different ways in order to ensure non-redundancy of the summary.
We consider three natural dispersion functions and show that a greedy algorithm can obtain an approximately optimal summary in all three cases. We conduct experiments on two corpora—DUC 2004 and user comments on news articles—and show that the performance of our algorithm outperforms algorithms that rely only on submodularity.
Conference Manager (V2.61.0 - Rev. 2792M)