A document-sensitive graph model for multi-document summarization

摘要: In recent years, graph-based models and ranking algorithms have drawn considerable attention from the extractive document summarization community. Most existing approaches take into account sentence-level relations (e.g. sentence similarity) but neglect difference among documents influence of on sentences. this paper, we present a novel document-sensitive graph model that emphasizes global set information local evaluation. By exploiting document–document document–sentence relations, distinguish intra-document inter-document relations. such way, move towards goal truly summarizing multiple rather than single combined document. Based model, develop an iterative algorithm, namely DsR (Document-Sensitive Ranking). Automatic ROUGE evaluations DUC data sets show outperforms previous in both generic query-oriented tasks.