摘要
本文提出了一种基于词共现图的文档自动摘要算法.该算法以统计方法为基础,又利用词共现图形成的主题信息以及不同主题间的连接特征信息,旨在能够有效地生成既全面反映文档的主要内容,又不受领域限制的文档摘要;同时该方法能动态地确定文档摘要长度.在实验评估中,该文档自动摘要方法取得了令人满意的摘要效果.
In this paper, an algorithm which automatically summarizes a document by word co-occurrence graph is described, which based on statistics and text subject information resulting from word co-occurrence graph and linkage information of different text subjects, in order to get better summarization and get rid of the restriction of information domain. Besides, the algorithm can dynamically obtain the proper document summarization length. Experiments show that this method can generate satisfying document summarization.
出处
《情报学报》
CSSCI
北大核心
2005年第6期651-656,共6页
Journal of the China Society for Scientific and Technical Information
基金
中国科学院资助项目
关键词
自动摘要
词共现图
主题
自然语言处理
automatic summarization, word co-occurrence, subject, natural language processing
