MR&MR-SUM: MAXIMUM RELEVANCE AND MINIMUM REDUNDANCY DOCUMENT SUMMARIZATION MODEL

作者：Alguliev Rasim M^*; Aliguliyev Ramiz M; Isazade Nijat R

来源：International Journal of Information Technology and Decision Making, 2013, 12(3): 361-393.

DOI：10.1142/S0219622013500156

• Unsupervised document summarization
• maximum relevance
• minimum redundancy
• quadratic integer programming
• differential evolution algorithm
• combined similarity measure

We have presented an approach to automatic document summarization. In the proposed approach, text summarization is modeled as a quadratic integer-programming problem. This model generally attempts to optimize three properties, namely, (1) relevance: summary should contain informative textual units that are relevant to the user; (2) redundancy: summaries should not contain multiple textual units that convey the same information; and (3) length: summary is bounded in length. To solve the optimization problem we have created a novel differential evolution algorithm. Experimental results on DUC2005 and DUC2007 data sets showed that the proposed approach outperforms the other methods. Doubt in Title

• 出版日期2013-5