Multi-document Summarization Using Bipartite Graphs

In this paper, we introduce a novel graph based technique for topic based multidocument summarization. We transform documents into a bipartite graph where one set of nodes represents entities and the other set of nodes represents sentences. To obtain the summary we apply a ranking technique to the bipartite graph which is followed by an optimization step. We test the performance of our method on several DUC datasets and compare it to the stateof-the-art.