摘要
基于关键词驱动的信息抽取系统的每个关键词都必须对应着相应的抽取规则。为了确保信息抽取系统具有较好的可移植性,设计了一种信息抽取规则描述语言。它由1-N条规则表达式构成。每条规则表达式由测试规则和提取规则两部分构成。它具有很强的描述能力和较高的处理效率,能满足信息抽取的实际需要。
Each keyword of the keywords driven information extraction system must have its information extraction rule. The article designs the description language of the rule of the information extraction which guarantees better portability of this system. It is made up of some rule formulas. Each rule formula is made up of two parts： test rule and extraction rule. It has strong description ability and high efficiency, and can meet actual needs of the information extraction.
出处
《软件导刊》
2009年第10期67-69,共3页
Software Guide
关键词
信息抽取
规则描述语言
关键词驱动
Information Extraction
Rule Description Language
Keywords Driven
