| 注册
首页|期刊导航|计算机应用研究|基于事件指导的多文档生成式摘要方法

基于事件指导的多文档生成式摘要方法

王振超 孙锐 姬东鸿

计算机应用研究2017,Vol.34Issue(2):343-346,356,5.
计算机应用研究2017,Vol.34Issue(2):343-346,356,5.DOI:10.3969/j.issn.1001-3695.2017.02.005

基于事件指导的多文档生成式摘要方法

Event-guided method for abstractive multi-document summarization

王振超 1孙锐 1姬东鸿1

作者信息

  • 1. 武汉大学计算机学院,武汉430072
  • 折叠

摘要

Abstract

multi-document summarzafion is often based on semantic analysis of texts.This method is more reasonable than the extractive method,but has to solve some problems like semantic analysis and natural language generation.This paper presented a novel abstractive method which treated event as basic semantic unit.It used events to represent the texts' topic distribution and direct multi-sentence compression to generate natural summary sentences.Experimental results on DUC compare favourably with state-of-the-art abstractive methods show that event is an ideal carrier for information and plays a positive role in multi-sentence compression.

关键词

事件/生成式/组合语义/子主题/多语句压缩/多文档摘要

Key words

event/abstractive/semantic combination/sub-topic/multi-sentence compression/multi-document summarization

分类

信息技术与安全科学

引用本文复制引用

王振超,孙锐,姬东鸿..基于事件指导的多文档生成式摘要方法[J].计算机应用研究,2017,34(2):343-346,356,5.

基金项目

国家社科重大招标计划资助项目(11&ZD189) (11&ZD189)

国家自然科学基金面上项目(61373108) (61373108)

计算机应用研究

OA北大核心CSCDCSTPCD

1001-3695

访问量0
|
下载量0
段落导航相关论文