摘要
本文将现有的自动文摘方法概括为四种:自动摘录、基于理解的自动文摘、信息抽取和基于结构的自动文摘,并详细介绍了这四种方法的基本原理,剖析了它们的优点和不足。最后,概述了中文自动文摘的研究状况。
In this paper,the existing methods of automatic abstracting are generalized to four kinds:automatic extraction,automatic abstracting based on understanding,information extraction,automatic abstracting based on structures.The principles of the four kinds of methods are described in detail,and the merits and defects are analyzed.In the end,the research status of Chinese automatic abstracting is outlined.
出处
《情报学报》
CSSCI
北大核心
1999年第1期10-19,共10页
Journal of the China Society for Scientific and Technical Information
关键词
自然语言处理
情报科学
自动文摘
natural language processing,information science,automatic abstracting.