Exploring events and distributed representations of text in multi-document summarization

作者：

Highlights：

• We explore an event detection framework to improve multi-document summarization

• We use distributed representations of text to address different lexical realizations

• Summarization is based on the hierarchical combination of single-document summaries

• We performed an automatic evaluation and a human study of the generated summaries

• Quantitative and qualitative results show clear improvements over the state-of-the-art

摘要

•We explore an event detection framework to improve multi-document summarization•We use distributed representations of text to address different lexical realizations•Summarization is based on the hierarchical combination of single-document summaries•We performed an automatic evaluation and a human study of the generated summaries•Quantitative and qualitative results show clear improvements over the state-of-the-art

论文关键词：Multi-document summarization,Extractive summarization,Event detection,Distributed representations of text

论文评审过程：Received 17 July 2015, Revised 25 September 2015, Accepted 5 November 2015, Available online 12 November 2015, Version of Record 7 January 2016.

论文官网地址：https://doi.org/10.1016/j.knosys.2015.11.005