Abstract | ||
---|---|---|
This article describes a new approach of HTML pages search via Internet, which is based on the semantic understanding of pages content by means of multi-agent technology. Multi-agent text understanding system, which is the basis of the approach, converts an input query and pages, received from conventional search engines, to formalized semantic descriptors, and evaluates similarity of these descriptors. Both text understanding and descriptor comparison algorithms use the knowledge about problem domain, represented in open and easy-to-update form of ontology. The approach developed was applied to the analysis of web-pages related to car industry. As a result a meta-search engine was developed, capable of analyzing pages, retrieved from traditional search engines and sorting pages by their semantic relevance to the user request. In this article one will find description of the system, testing results and future perspectives. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1007/978-3-540-72839-9_22 | AIS-ADM |
Keywords | Field | DocType |
multi-agent text understanding system,domain ontology,traditional search engine,multi-agent meta-search engine,pages content,semantic relevance,html pages search,semantic understanding,text understanding,new approach,formalized semantic descriptors,conventional search engine,web pages,meta search engine,formal semantics,search engine,semantic network | Semantic similarity,Data mining,Metasearch engine,Semantic search,Information retrieval,Semantic Web Stack,Computer science,Full text search,Search engine indexing,Search analytics,Spamdexing | Conference |
Volume | ISSN | Citations |
4476 | 0302-9743 | 2 |
PageRank | References | Authors |
0.46 | 1 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marat Kanteev | 1 | 2 | 0.46 |
Igor Minakov | 2 | 11 | 1.71 |
George Rzevski | 3 | 69 | 12.37 |
Petr Skobelev | 4 | 118 | 24.61 |
Simon Volman | 5 | 11 | 1.71 |