Multiple News Articles Summarization Based on Event Reference Information

Multiple News Articles Summarization Based on Event Reference Information
复制标题

DOI:
--
复制
发表时间:
2004
期刊:
--
影响因子:
--
通讯作者:
Masaharu Yoshioka;M. Haraguchi
Masaharu Yoshioka;M. Haraguchi
中科院分区:
其他
文献类型:
--
作者:
Masaharu Yoshioka;M. Haraguchi

文献摘要

被引文献

相似文献

在本文中,我们描述了从多篇新闻文章生成摘要的方法。由于大多数新闻文章都会报道多个事件,并且这些事件会在后续文章中引用,因此我们使用此事件引用信息来计算句子在多篇新闻文章中的重要性。我们还提出了一种利用事件相似性删除冗余描述的方法。最后根据评价结果讨论其有效性。
In this paper, we describe our method to generate summary from multiple news articles. Since most of news articles report several events and these events are refereed with following articles, we use this event reference information to calculate importance of a sentence in multiple news articles. We also propose a method to delete redundant description by using similarity of events. Finally we discuss its effectiveness based on the evaluation result.