Word-sentence co-ranking for automatic extractive text summarization

作者：

Highlights：

• A principled word-sentence co-ranking model called CoRank is proposed.

• The convergence of CoRank with matrix notation is proved.

• A redundancy elimination technique is presented to further improve the performance of CoRank.

摘要

•A principled word-sentence co-ranking model called CoRank is proposed.•The convergence of CoRank with matrix notation is proved.•A redundancy elimination technique is presented to further improve the performance of CoRank.

论文关键词：Automatic summarization,Extractive summary,Sentence scoring,Pagerank,Unsupervised learning

论文评审过程：Received 5 March 2016, Revised 11 December 2016, Accepted 13 December 2016, Available online 15 December 2016, Version of Record 23 December 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.12.021