Semantic representation of scientific documents for the e-science Knowledge Grid

Authors:
Xiangfeng Luo;Ning Fang;Bo Hu;Kai Yan;Huizhe Xiao
Affiliations:
Digital Content Computing and Semantic Grid Group, Key Lab. of Grid Technology, Shanghai University, Shanghai 200072, China;Digital Content Computing and Semantic Grid Group, Key Lab. of Grid Technology, Shanghai University, Shanghai 200072, China;Digital Content Computing and Semantic Grid Group, Key Lab. of Grid Technology, Shanghai University, Shanghai 200072, China;Digital Content Computing and Semantic Grid Group, Key Lab. of Grid Technology, Shanghai University, Shanghai 200072, China;Digital Content Computing and Semantic Grid Group, Key Lab. of Grid Technology, Shanghai University, Shanghai 200072, China
Venue:
Concurrency and Computation: Practice & Experience - Second International Conference on Semantics, Knowledge and Grid (SKG2006)
Year:
2008

Citing 0
Cited 4

Merging element fuzzy cognitive maps

Proceedings of the 3rd International Conference on Ubiquitous Information Management and Communication
Building associated semantic overlay for discovering associated services

ICIC'10 Proceedings of the 6th international conference on Advanced intelligent computing theories and applications: intelligent computing
Learning path construction based on association link network

ICWL'12 Proceedings of the 11th international conference on Advances in Web-Based Learning
Discovering small-world in association link networks for association learning

World Wide Web

Quantified Score

Hi-index	0.00

Visualization

Abstract

Semantic representation of a topic is the basic element representation of a scientific document, which can be reflected by keywords' relations and their weights, as well as the state values of co-occurring keywords in a documental fragment in which a topic is discussed. Concept lattice and probability statistical methods are proposed to generate fuzzy cognitive maps (FCMs) as the original semantic representation of documental fragments (SRDFs) for the e-science Knowledge Grid. The additive capability of FCMs is used to merge SRDFs for reducing the noise and redundant information hidden in the original SRDFs. The loss of documental information in the merging process of SRDFs is measured by the proposed semantic merging entropy. Based on the distributional property of keywords on SRDFs, semantic distribution entropy is introduced to evaluate the change of keywords' distribution on SRDFs with the merging process. The semantic representation of a scientific document is automatically generated by the interconnection of the merged SRDFs belonging to one domain. The generating, merging and evaluating methods of the semantic representation of a scientific document are validated by experiments. The proposed semantic representation highlights the relations among keywords and topics, which reduces the complexity of document analysis in an e-science Knowledge Grid effectively. Copyright © 2007 John Wiley & Sons, Ltd.