A document-sensitive graph model for multi-document summarization

Furu Wei, Wenjie Li, Qin Lu, Yanxiang He

Research output: Journal article publicationJournal articleAcademic researchpeer-review

57 Citations (Scopus)

Abstract

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 the difference among documents and the influence of documents on sentences. In this paper, we present a novel document-sensitive graph model that emphasizes the influence of global document set information on local sentence evaluation. By exploiting document-document and document-sentence relations, we distinguish intra-document sentence relations from inter-document sentence relations. In such a way, we move towards the goal of truly summarizing multiple documents rather than a single combined document. Based on this model, we develop an iterative sentence ranking algorithm, namely DsR (Document-Sensitive Ranking). Automatic ROUGE evaluations on the DUC data sets show that DsR outperforms previous graph-based models in both generic and query-oriented summarization tasks.
Original languageEnglish
Pages (from-to)245-259
Number of pages15
JournalKnowledge and Information Systems
Volume22
Issue number2
DOIs
Publication statusPublished - 1 Feb 2010

Keywords

  • Generic summarization
  • Graph-based ranking algorithm
  • Graph-based summarization model
  • Inter- and intra-document relation
  • Query-oriented summarization

ASJC Scopus subject areas

  • Software
  • Information Systems
  • Human-Computer Interaction
  • Hardware and Architecture
  • Artificial Intelligence

Cite this