自动摘要方法综述  

Literature Review of Automatic Summarization Methods

作　　者：谭翀[1] 陈跃新[1] 

机构地区：[1]国防科学技术大学计算机学院,长沙410073

出　　处：《情报学报》2008年第1期62-68,共7页Journal of the China Society for Scientific and Technical Information

摘　　要：自动摘要是计算机语言学领域的一个研究重点，自动摘要的研究和应用受到了计算机学、语言学、认知心理学等相关学科的广泛关注。本文讨论了摘要的定义及其分类。依据自动摘要的特点对其分类，并作为构造自动摘要系统和思考自动摘要技术发展的参考和启示。本文概述了自动摘要的发展历史和研究现状。并将现有的自动摘要方法分为三类，分别阐述了这三类方法的基本特征和研究方法，并剖析了它们的优点和不足。本文着重讨论了基于篇章结构的方法的几个不同研究方向及其局限和趋势。最后，文章讨论了自动摘要研究存在的问题，并指出自动摘要的研究趋势。Automatic Summarization technology is a main field of Computational Linguistics, the studying and application of automatic summarization has widely attracted the attention of interrelated academic subjects such as computers science, linguistics, and cognitive psychology. This paper discusses the definition and classifications of summary. The classification of the automatic summarization contributed to the construction of automatic summarization and the development of automatic summarization technology is based on the features of automatic summarization. This paper also outlines the historical development of automatic smnmarization and describes the current research methodology, classifies them into three categories by existing technologies and methods, respectively, discusses the basic character and research methods of the three categories, and analyzes the merits and defects as well. This paper emphasizes the text structure-based method, and introduces several research directions and their localization and trend. In the end, the existing problem and the developing trend of automatic summarization technology are discussed.

关 键 词：自动摘要 方法论 计算机语言学 篇章结构 

分 类 号：G356.7[文化科学—情报学] TP312[自动化与计算机技术—计算机软件与理论]