摘要
文章把关键词自动抽取拆分为3个阶段的问题:如何进行文本预处理;怎样获得关键词候选词集;该采用什么方法从候选词集中筛选出关键词。首先针对不同阶段的问题,详细地介绍现有的典型方法。然后介绍了关键词自动抽取技术最新的研究进展,并分析了关键词自动抽取技术的发展趋势。最后指出了目前关键词自动抽取技术研究的不足之处。
In this paper keyword automatic extraction technologies are divided and articulated as 3 stages: 1 how to preprocess the text; 2 how to get the candidate keyword set; 3 how to select the keywords from the candidate keyword set.The paper first introduces the typical methods for different stages.Then,the paper introduces the latest research of keyword extraction technology,and analyzes the development trend of keyword extraction technology.At the end of the paper,the shortcomings of the research on keyword extraction technology are pointed out.
出处
《情报理论与实践》
CSSCI
北大核心
2016年第7期141-144,共4页
Information Studies:Theory & Application
关键词
关键词
自动抽取
研究进展
综述
automatic extraction
research progress
review