{"id":"https://openalex.org/W2165708596","doi":"https://doi.org/10.1109/icdim.2008.4746764","title":"A fast approximate algorithm for large-scale Latent Semantic Indexing","display_name":"A fast approximate algorithm for large-scale Latent Semantic Indexing","publication_year":2008,"publication_date":"2008-11-01","ids":{"openalex":"https://openalex.org/W2165708596","doi":"https://doi.org/10.1109/icdim.2008.4746764","mag":"2165708596"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2008.4746764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third International Conference on Digital Information Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015784640","display_name":"Dell Zhang","orcid":"https://orcid.org/0000-0002-8774-3725"},"institutions":[{"id":"https://openalex.org/I98259816","display_name":"Birkbeck, University of London","ror":"https://ror.org/02mb95055","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I98259816"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Dell Zhang","raw_affiliation_strings":["SCSIS Birkbec, University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"SCSIS Birkbec, University of London, London, UK","institution_ids":["https://openalex.org/I98259816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054190140","display_name":"Zheng Zhu","orcid":"https://orcid.org/0000-0001-7510-9949"},"institutions":[{"id":"https://openalex.org/I98259816","display_name":"Birkbeck, University of London","ror":"https://ror.org/02mb95055","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I98259816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zheng Zhu","raw_affiliation_strings":["SCSIS Birkbec, University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"SCSIS Birkbec, University of London, London, UK","institution_ids":["https://openalex.org/I98259816"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015784640"],"corresponding_institution_ids":["https://openalex.org/I98259816"],"apc_list":null,"apc_paid":null,"fwci":0.3798,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66069334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"626","last_page":"631"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.82236248254776},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.747020959854126},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5501393675804138},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.5498261451721191},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5344433188438416},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4957209825515747},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4932035803794861},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44686147570610046},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4155963361263275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2764503061771393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.82236248254776},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.747020959854126},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5501393675804138},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.5498261451721191},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5344433188438416},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4957209825515747},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4932035803794861},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44686147570610046},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4155963361263275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2764503061771393},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icdim.2008.4746764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third International Conference on Digital Information Management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.144.4595","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.144.4595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcs.bbk.ac.uk/~dell/publications/dellzhang_icdim2008b.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.bbk.ac.uk.oai2:7079","is_oa":false,"landing_page_url":"https://eprints.bbk.ac.uk/id/eprint/7079/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400466","display_name":"BIROn (Birkbeck, University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98259816","host_organization_name":"Birkbeck, University of London","host_organization_lineage":["https://openalex.org/I98259816"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book Section"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W174106550","https://openalex.org/W658559791","https://openalex.org/W1487444668","https://openalex.org/W1493526108","https://openalex.org/W1496147749","https://openalex.org/W1500092210","https://openalex.org/W1532325895","https://openalex.org/W1878377492","https://openalex.org/W1970576574","https://openalex.org/W1970950689","https://openalex.org/W2003690406","https://openalex.org/W2042465463","https://openalex.org/W2063392856","https://openalex.org/W2072773380","https://openalex.org/W2073414385","https://openalex.org/W2096863518","https://openalex.org/W2110063061","https://openalex.org/W2123977795","https://openalex.org/W2138451337","https://openalex.org/W2138621811","https://openalex.org/W2147152072","https://openalex.org/W2148541040","https://openalex.org/W2162491638","https://openalex.org/W2534415968","https://openalex.org/W2610857016","https://openalex.org/W2798909945","https://openalex.org/W2946046356","https://openalex.org/W2992809543","https://openalex.org/W3145128584","https://openalex.org/W3150353689","https://openalex.org/W4213009331","https://openalex.org/W4285719527","https://openalex.org/W4301621763","https://openalex.org/W6607136368","https://openalex.org/W6629760660","https://openalex.org/W6684281289","https://openalex.org/W6729054657","https://openalex.org/W6771715580"],"related_works":["https://openalex.org/W4389358162","https://openalex.org/W2111020819","https://openalex.org/W2377594161","https://openalex.org/W1837533151","https://openalex.org/W2296297476","https://openalex.org/W2329943782","https://openalex.org/W1578340400","https://openalex.org/W2365514879","https://openalex.org/W84513934","https://openalex.org/W15987807"],"abstract_inverted_index":{"Latent":[0],"semantic":[1,12],"indexing":[2],"(LSI)":[3],"is":[4,55,64],"an":[5],"effective":[6],"method":[7],"to":[8,38,65],"discover":[9],"the":[10,27,68],"underlying":[11],"structure":[13],"of":[14,30],"data.":[15],"It":[16],"has":[17,71],"numerous":[18],"applications":[19],"in":[20],"information":[21],"retrieval":[22],"and":[23,58,75],"data":[24],"mining.":[25],"However,":[26],"computational":[28,77],"complexity":[29],"LSI":[31,53],"may":[32],"be":[33],"prohibitively":[34],"high":[35],"when":[36],"applied":[37],"very":[39],"large":[40],"datasets.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"present":[46],"a":[47],"fast":[48],"approximate":[49],"algorithm":[50,70],"for":[51],"large-scale":[52],"that":[54,67],"conceptually":[56],"simple":[57],"theoretically":[59],"justified.":[60],"Our":[61],"main":[62],"contribution":[63],"show":[66],"proposed":[69],"provable":[72],"error":[73],"bound":[74],"linear":[76],"complexity.":[78]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
