Research on Information Extraction Based on Web Table Structure and Ontology

Abstract:

With the rapid development of the Internet, as well as the increasingly large Web data, enabling users to obtain useful information from the Web is becoming increasingly difficult, From the Web, how to quickly and efficiently and accurately extract information has become an urgent problem, the Web information extraction technology came into being. Through a Web table positioning, Web table structure identification, the Web table content integration and extraction of results and so on four areas, Proposed a Web-based table structure extraction method. It has good versatility and high accuracy.

• Periodical: Applied Mechanics and Materials (Volumes 321-324)
• Pages: 2254-2259
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.321-324.2254
• Online since: June 2013
• Authors: Xiao Feng Wang
• Keywords: Heuristic Rules, Information Extraction, Ontology Library, Web Table, XML

References

[1] Zhao Hong, Xiao Hong, Xue Dejun, Shi Qinghui. Study on Web table Information extraction [J]. Modern Library and Information Technology, 2008(3), pp.24-29.(In Chinese)

[2] Liao Tao,Liu Zongtian,Kong Qingping. The design and realization of Web table information extraction model [J]. Computer Applications and Software, 2009(4), pp.72-74. (In Chinese)

[3] Wang Fang, GU Ning, Wu Guowen. Web table information extraction based on ontology [J]. Mini-Micro Systems, 2003, 24(12), pp.2142-2146. (In Chinese)

[4] Lin Lin. The study and realization of Web table content extraction based on ontology [M].ChenDu: University of Electronic Science and Technology, 2006. (In Chinese)

[5] Xu Wen, Du Yuncheng, Li Yuqin. A generic HTML page thematic information extraction [J]. Modern Library and Information Technology, 2007(1), pp.40-43. (In Chinese)

[6] Zhang Rui,Li Shijun.Automatic coversion of HTML tables into XML[J].Computer Engineering and Applications,2007,43(2):190-192. (In Chinese)