Amplifying scientific paper’s abstract by leveraging data-weighted reconstruction
作者：
Highlights：
• This paper explores the impact of heterogeneous bibliographic network for generating scientific paper’s amplified abstract.
• The amplified abstract is generated by leveraging target scientific paper’s abstract and citation sentence’s content and structure, which is addressed through document summarization manner.
• Sentence’s weight is learned by exploiting regularization for ranking on heterogeneous bibliographic network.
• Data-weighted reconstruction is proposed to assign different priority to sentences when reconstructing the original document.
• Various evaluation metrics are designed to validate the effectiveness of our approach.
摘要
•This paper explores the impact of heterogeneous bibliographic network for generating scientific paper’s amplified abstract.•The amplified abstract is generated by leveraging target scientific paper’s abstract and citation sentence’s content and structure, which is addressed through document summarization manner.•Sentence’s weight is learned by exploiting regularization for ranking on heterogeneous bibliographic network.•Data-weighted reconstruction is proposed to assign different priority to sentences when reconstructing the original document.•Various evaluation metrics are designed to validate the effectiveness of our approach.
论文关键词：Document summarization,Citation analysis,Scientific literature,Data-weighted reconstruction
论文评审过程：Received 10 December 2014, Revised 21 December 2015, Accepted 25 December 2015, Available online 18 January 2016, Version of Record 17 May 2016.
论文官网地址：https://doi.org/10.1016/j.ipm.2015.12.014
