摘要
并列结构在文本中出现的几率很高,但并列结构识别的准确率并不高,并列结构识别一直是自然语言处理的一个难点。文章对国内外学者提出的并列结构的识别方法进行总结与综述,介绍了基于规则的和基于统计的较为典型的识别方法。
Probability of coordinate structure appears in the text is very high, but the accuracy of coordination identification is not high, coordination identification has always been a difficult problem in natural language processing. In this paper, we summarized and reviewed the coordination identification methods on the domestic and foreign scholars. Some typical methods were summarized, base on rules and base on statistics.
出处
《电脑与信息技术》
2014年第3期38-40,共3页
Computer and Information Technology
关键词
并列结构
识别
规则
统计
coordination
identification
rules
statistics
