A progressive sentence selection strategy for document summarization

• Published in: Information processing & management 2013-01, Vol.49 (1), p.213-221
• Main Authors: Ouyang, You, Li, Wenjie, Zhang, Renxian, Li, Sujian, Lu, Qin
• Format: Article
• Language: English
• Subjects: Asymmetric sentence relationship; Automatic abstracting; Data processing; Document summarization; Documents; Exact sciences and technology; Information and communication sciences; Information processing; Information processing and retrieval; Information retrieval systems. Information and document management system; Information retrieval. Man machine relationship; Information science. Documentation; Management; Priorities; Progressive sentence selection; Redundancy; Research process. Evaluation; Saliency and coverage; Sciences and techniques of general use; Selection; Sentences; Strategy; Studies; Summaries; Syntax
• ISSN: 0306-4573; 1873-5371
• DOI: 10.1016/j.ipm.2012.05.002

► Study the subsuming relationship between sentences. ► Define the conditional saliency of a new sentence to the already-selected sentences. ► Progressively select summary sentences to ensure the saliency and coverage of the summary. Saliency and coverage are two of the most important issues in document summarization. In most summarization methods, the saliency issue is usually of top priority. Many studies are conducted to develop better sentence ranking methods to identify the salient sentences for summarization. It is also well acknowledged that sentence selection strategies are very important, which mainly aim at reducing the redundancy among the selected sentences to enable them to cover more concepts. In this paper, we propose a novel sentence selection strategy that follows a progressive way to select the summary sentences. We intend to ensure the coverage of the summary first by an intuitive idea, i.e., considering the uncovered concepts only when measuring the saliency of the sentences. Moreover, we consider the subsuming relationship between sentences to define a conditional saliency measure of the sentences instead of the general saliency measures used in most existing methods. Based on these ideas, a progressive sentence selection strategy is developed to discover the “novel and salient” sentences. Compared with traditional methods, the saliency and coverage issues are more integrated in the proposed method. Experimental studies conducted on the DUC data sets demonstrate the advantages of the progressive sentence selection strategy.