摘要
自动文摘是自然语言处理的一个重要分支,在信息检索领域中有着重要的用途,文本自动综述是自动文摘在多文档上的推广。本文提出了基于实体名扩展的自动综述方法,这种方法认为综述中的实体名个数反映其中所蕴合信息量的多少。我们用该方法实现针对事件的自动综述生成,并参加了2003年文本理解会议(Document UnderstandingConference,DUC)进行统一评测,DUC反馈的评测结果显示这种方法是有效的。此外,本文还对文本理解会议的任务、评测方法和测试结果做了简单介绍。
Text Summarization is one important branch of Natural Language Processing and is very useful in Information Retrieval. This paper presents an approach of automatic text summarization based on Named Entity. This approach assumes that the number of Named Entities in a summary reflects the amount of information in it. By this approach we generate the summaries focused by events which are submitted to and evaluated by Document Understanding Conference 2003. The results of the evaluation show that this approach is effective. This paper also introduces the Document Understanding Conference.
出处
《计算机科学》
CSCD
北大核心
2004年第9期161-164,共4页
Computer Science
基金
国家自然科学基金(69935010
60103014)
863项目(2001AA114120
2002AA142090)资助