文章基本信息

标题：A CALCULATION METHOD OF DEEP WEB ENTITIES RECOGNITION
本地全文：下载
作者：FENG YONG ; DANG XIAO-WAN ; XU HONG-YAN 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2013
卷号：47
期号：3
出版社：Journal of Theoretical and Applied
摘要：A great amount of duplicated entities exist in the heterogeneous data sources of Web. How to identify these entities is the most important prerequisite for pattern matching and data integration. To solve the deficiency of current entity recognition methods, such as low automatic level and poor adaptability, Deep Web entity recognition method based on BP neural network is proposed in this paper. To make full use of the characteristic of autonomic learning of BP neural network, the similarities of semantic blocks are used as the input of BP neural network. It obtains correct entity recognition model through training, and accomplishes the target of automated entity recognition of heterogeneous data sources. Finally, the feasibility of the proposed method is verified via experiments. The proposed method can reduce manual intervention and promote the efficiency and the accuracy of entity recognition simultaneously.
关键词：Deep Web; BP Neural Network; Entities Identify; Similarity