Abstract | ||
---|---|---|
This paper is concerned with the problem of semantic search. By semantic search, we mean searching for instances from knowledge base. Given a query, we are to retrieve ‘relevant’ instances, including those that contain the query keywords and those that do not contain the keywords. This is contrast to the traditional approaches of generating a ranked list of documents that contain the keywords. Specifically, we first employ keyword based search method to retrieve instances for a query; then a proposed method of semantic feedback is performed to refine the search results; and then we conduct re-retrieval by making use of relations and instance similarities. To make the search more effective, we use weighted ontology as the underlying data model in which importances are assigned to different concepts and relations. As far as we know, exploiting instance similarities in search on weighted ontology has not been investigated previously. For the task of instance similarity calculation, we exploit both concept hierarchy and properties. We applied our methods to a software domain. Empirical evaluation indicates that the proposed methods can improve the search performance significantly. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11610113_44 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
semantic similarity,weighted ontology-based search,semantic feedback,instance similarity calculation,weighted ontology,search performance,query keyword,search method,instance similarity,search result,semantic search,ontology,data models,search algorithm,knowledge base,search problem,data model,similarity,case based reasoning,semantics,similitude | Semantic similarity,Ontology,Data mining,Web search query,Search algorithm,Information retrieval,Semantic search,Phrase search,Computer science,Search problem,Semantics,Database | Conference |
Volume | ISSN | ISBN |
3841 | 0302-9743 | 3-540-31142-4 |
Citations | PageRank | References |
10 | 0.72 | 12 |
Authors | ||
5 |