Show simple item record

dc.contributor.authorPan, Qi
dc.contributor.authorHadzic, Fedja
dc.contributor.authorDillon, Tharam S.
dc.contributor.editorColin Fyfe
dc.contributor.editorPeter Tino
dc.contributor.editorDarryl Charles
dc.contributor.editorCesar Garcia-Osorio
dc.contributor.editorHujunYin
dc.date.accessioned2017-01-30T10:56:06Z
dc.date.available2017-01-30T10:56:06Z
dc.date.created2011-03-22T20:01:31Z
dc.date.issued2010
dc.identifier.citationPan, Qi H. and Hadzic, Fedja and Dillon, Tharam S. 2010. Discovering Concept Mappings by Similarity Propagation among Substructures, in Fyfe, C. and Tino, P. and Charles, D. and Garcia-Osorio, C. and Yin, H. (ed), Lecture Notes in Computer Science, Volume 6283: Intelligent Data Engineering and Automated Learning – IDEAL 2010. pp. 324-333. Germany: Springer.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/6865
dc.description.abstract

Concept matching is important when heterogeneous data sources are to be merged for the purpose of knowledge sharing. It has many useful applications in areas such as schema matching, ontology matching, scientific knowledge management, e-commerce, enterprise application integration, etc. With the desire of knowledge sharing and reuse in these fields, merging commonly occurs among different organizations where the knowledge describing the same domain is to be matched. Due to the different naming conventions, granularity and the use of concepts in different contexts, a semantic approach to this problem is preferred in comparison to syntactic approach that performs matches based upon the labels only. We propose a concept matching method that initially does not consider labels when forming candidate matches, but rather utilizes structural information to take the context into account and detect complex matches. Real world knowledge representations (schemas) are used to evaluate the method.

dc.publisherSpringer
dc.subjectschema matching
dc.subjectconcept matching
dc.subjecttree mining
dc.titleDiscovering Concept Mappings by Similarity Propagation among Substructures
dc.typeBook Chapter
dcterms.source.startPage324
dcterms.source.endPage333
dcterms.source.titleLecture notes in computer science, volume 6283: intelligent data engineering and automated learning (IDEAL 2010)
dcterms.source.isbn9783642153808
dcterms.source.placeHeidelberg
dcterms.source.chapter47
curtin.departmentCentre for Extended Enterprises and Business Intelligence
curtin.accessStatusFulltext not available


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record