一种基于语义及统计分析的DeepWeb实体识别机制  

A Deep Web Entity Identification Mechanism Based on Semantics and Statistical Analysis

作　　者：寇月[1] 申德荣[1] 李冬[2] 聂铁铮[1] 

机构地区：[1]东北大学信息科学与工程学院,辽宁沈阳110004 [2]东软集团有限公司商用软件事业部,辽宁沈阳110179

出　　处：《软件学报》2008年第2期194-208,共15页Journal of Software

基　　金：Supported by the National Natural Science Foundation of China under Grant No.60673139 (国家自然科学基金)

摘　　要：分析了常见的实体识别方法,提出了一种基于语义及统计分析的实体识别机制(deep Web entity identification mechanism based on semantics and statistical analysis,简称SS-EIM),能够有效解决Deep Web数据集成中数据纠错、消重及整合等问题.SS-EIM主要由文本匹配模型、语义分析模型和分组统计模型组成,采用文本粗略匹配、表象关联关系获取以及分组统计分析的三段式逐步求精策略,基于文本特征、语义信息及约束规则来不断精化识别结果;根据可获取的有限的实例信息,采用静态分析、动态协调相结合的自适应知识维护策略,构建和完善表象关联知识库,以适应Web数据的动态性并保证表象关联知识的完备性.通过实验验证了SS-EIM中所采用的关键技术的可行性和有效性.According to analyzing the traditional entity identification methods, a deep Web entity identification mechanism based on semantics and statistical analysis （SS-EIM） is presented in this paper, which includes text matching model, semantics analysis model and group statistics model. Also a three-phase gradual refining strategy is adopted, which includes text initial matching, representation relationship abstraction and group statistics analysis. Based on the text characteristics, semantic information and constraints, the identification result is revised continuously to improve the accuracy. By performing the self-adaptive knowledge maintenance strategy, the content of representation relationship knowledge database can be more complete and effective. The experiments demonstrate the feasibility and effectiveness of the key techniques of SS-EIM.

关 键 词：DEEP WEB 数据集成 实体识别 数据消重 表象整合 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]