Query-focused multi-document summarization using hypergraph-based ranking
作者：
Highlights：
• We propose a novel hybrid method to capture group relation of sentences.
• We cluster sentences with a KL-divergence based on word-topic distribution.
• We proposed a vertex reinforcement random walk process in a hypergraph model.
• The process simultaneously consider the query similarity, the centrality and the diversity of sentences.
• We implement our framework and verify improvement over appropriate baselines.
摘要
•We propose a novel hybrid method to capture group relation of sentences.•We cluster sentences with a KL-divergence based on word-topic distribution.•We proposed a vertex reinforcement random walk process in a hypergraph model.•The process simultaneously consider the query similarity, the centrality and the diversity of sentences.•We implement our framework and verify improvement over appropriate baselines.
论文关键词：Multi-document summarization,Hypergraph-based ranking,HDP
论文评审过程：Received 13 January 2015, Revised 29 November 2015, Accepted 22 December 2015, Available online 19 January 2016, Version of Record 17 May 2016.
论文官网地址：https://doi.org/10.1016/j.ipm.2015.12.012
