CAJ | 학술논문

如何从互联网web页面中快速、准确获得用户感兴趣的数据内容成为信息抽取领域的研究热点。本文总结现有Web信息抽取分类方法，并提出按用户参与程度对Web信息抽取系统进行分类的方法，分为人工创建系统、用户监督系统和无人监督系统，并从7个方面对Web信息抽取系统进行分析、比较。
여하종호련망web혈면중쾌속、준학획득용호감흥취적수거내용성위신식추취영역적연구열점。본문총결현유Web신식추취분류방법，병제출안용호삼여정도대Web신식추취계통진행분류적방법，분위인공창건계통、용호감독계통화무인감독계통，병종7개방면대Web신식추취계통진행분석、비교。
How to obtain accurate and efficient information from the web has been a hot spot in information extraction field. This paper summarizes the classification method of the existing web information extraction, and classifies these web information extraction systems according to user's participation level, divides these web infolanation extraction systems into Manual - created systems, User - superv/sed systems and Un - supervised systems, and this paper analyzes and compares these web information extraction systems from seven aspects.