Show simple item record

dc.contributor.authorChen, Hsinchun
dc.contributor.authorZhang, Yin
dc.contributor.authorHouston, Andrea L.
dc.date.accessioned2004-09-20T00:00:01Z
dc.date.available2010-06-18T23:26:01Z
dc.date.issued1998en_US
dc.date.submitted2004-09-20en_US
dc.identifier.citationSemantic Indexing and Searching Using a Hopfield Net 1998, 24(1):3-18 Journal of Information Scienceen_US
dc.identifier.urihttp://hdl.handle.net/10150/105466
dc.descriptionArtificial Intelligence Lab, Department of MIS, University of Arizonaen_US
dc.description.abstractThis paper presents a neural network approach to document semantic indexing. A Hopfield net algorithm was used to simulate human associative memory for concept exploration in the domain of computer science and engineering. INSPEC, a collection of more than 320,000 document abstracts from leading journals, was used as the document testbed. Benchmark tests confirmed that three parameters (maximum number of activated nodes, E - maximum allowable error, and maximum number of iterations) were useful in positively influencing network convergence behavior without negatively impacting central processing unit performance. Another series of benchmark tests was performed to determine the effectiveness of various filtering techniques in reducing the negative impact of noisy input terms. Preliminary user tests confirmed our expectation that the Hopfield net algorithm is potentially useful as an associative memory technique to improve document recall and precision by solving discrepancies between indexer vocabularies and end-user vocabularies.
dc.format.mimetypeapplication/pdfen_US
dc.language.isoenen_US
dc.subjectArtificial Intelligenceen_US
dc.subjectIndexingen_US
dc.subject.otherNational Science Digital Libraryen_US
dc.subject.otherNSDLen_US
dc.subject.otherArtificial intelligence laben_US
dc.subject.otherAI laben_US
dc.subject.otherHopfield net algorithmen_US
dc.titleSemantic Indexing and Searching Using a Hopfield Neten_US
dc.typeJournal Article (Paginated)en_US
dc.identifier.journalJournal of Information Scienceen_US
refterms.dateFOA2018-08-21T12:11:44Z
html.description.abstractThis paper presents a neural network approach to document semantic indexing. A Hopfield net algorithm was used to simulate human associative memory for concept exploration in the domain of computer science and engineering. INSPEC, a collection of more than 320,000 document abstracts from leading journals, was used as the document testbed. Benchmark tests confirmed that three parameters (maximum number of activated nodes, E - maximum allowable error, and maximum number of iterations) were useful in positively influencing network convergence behavior without negatively impacting central processing unit performance. Another series of benchmark tests was performed to determine the effectiveness of various filtering techniques in reducing the negative impact of noisy input terms. Preliminary user tests confirmed our expectation that the Hopfield net algorithm is potentially useful as an associative memory technique to improve document recall and precision by solving discrepancies between indexer vocabularies and end-user vocabularies.


Files in this item

Thumbnail
Name:
chen20.pdf
Size:
4.312Mb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record