MCRMR: Maximum coverage and relevancy with minimal redundancy based multi-document summarization
作者：
Highlights：
• Proposed an unsupervised model for single document generation from multiple documents.
• Proposed a supervised model for sentence extraction.
• Exploited the strength of Shark Smell Optimization.
• Fusion of Word Mover’s Distance and Normalized Google Distance performed better.
• Experimented on six datasets to show the effectiveness of proposed method.
摘要
•Proposed an unsupervised model for single document generation from multiple documents.•Proposed a supervised model for sentence extraction.•Exploited the strength of Shark Smell Optimization.•Fusion of Word Mover’s Distance and Normalized Google Distance performed better.•Experimented on six datasets to show the effectiveness of proposed method.
论文关键词：Multi-document summarization,Word Mover’s distance,Normalized google distance,Shark smell optimization,Coverage,Non-redundancy
论文评审过程：Received 28 July 2018, Revised 1 November 2018, Accepted 13 November 2018, Available online 13 November 2018, Version of Record 16 November 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.11.022
