基于Web的命名实体提取的研究方法

Web是一个巨大的知识库,作为知识的载体,Web上的海量网页数据包含了各种各样的内容,在这些内容中,命名实体(named entity)是一类重要的内容.随着Web规模的指数级膨胀,如何在海量Web信息中定位自己所需的信息,成为一个非常紧迫的需要.本文结合大量相关文献,对Web命名实体提取的研究工作进行了介绍、分析与比较,并指出了以后努力的方向.

Research of Web-based named entity extraction

Web is a huge knowledge base.As the carrier of knowledge,the data of mass web includes varied contents in which named entity is the important part.As expend of the exponential series of Web scope,how to find the massage we need in the mass Web become urgent.This paper introduces the major studies,analyzes and compares the methods on the named entity,and point out the future direction in the area of web-based named entity extraction.