{"id":"https://openalex.org/W1997556310","doi":"https://doi.org/10.1145/1376616.1376717","title":"Discovering topical structures of databases","display_name":"Discovering topical structures of databases","publication_year":2008,"publication_date":"2008-06-09","ids":{"openalex":"https://openalex.org/W1997556310","doi":"https://doi.org/10.1145/1376616.1376717","mag":"1997556310"},"language":"en","primary_location":{"id":"doi:10.1145/1376616.1376717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376616.1376717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 ACM SIGMOD international conference on Management of data","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/A5061069727","display_name":"Wensheng Wu","orcid":"https://orcid.org/0000-0002-2948-9773"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wensheng Wu","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036119025","display_name":"Berthold Reinwald","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Berthold Reinwald","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048704801","display_name":"Yannis Sismanis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yannis Sismanis","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042211508","display_name":"Rajesh Manjrekar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajesh Manjrekar","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061069727"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":6.9982,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.96494886,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1019","last_page":"1030"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994999766349792,"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/T11106","display_name":"Data Management and Algorithms","score":0.9983000159263611,"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/T11719","display_name":"Data Quality and Management","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8273186683654785},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6451094150543213},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.5401962399482727},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.501300573348999},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5009574890136719},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4876040518283844},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48461660742759705},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.455780953168869},{"id":"https://openalex.org/keywords/database-theory","display_name":"Database theory","score":0.44764894247055054},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4459277093410492},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4323580265045166},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.42278343439102173},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41772398352622986},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.3283567428588867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16932734847068787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8273186683654785},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6451094150543213},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.5401962399482727},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.501300573348999},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5009574890136719},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4876040518283844},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48461660742759705},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.455780953168869},{"id":"https://openalex.org/C12439846","wikidata":"https://www.wikidata.org/wiki/Q4809258","display_name":"Database theory","level":3,"score":0.44764894247055054},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4459277093410492},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4323580265045166},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.42278343439102173},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41772398352622986},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.3283567428588867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16932734847068787},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1376616.1376717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376616.1376717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.141.6156","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.6156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.buffalo.edu/~mpetropo/CSE705-FA08/pubs/p1019-wu.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W194960720","https://openalex.org/W1508608166","https://openalex.org/W1525949272","https://openalex.org/W1549729095","https://openalex.org/W1563062065","https://openalex.org/W1578099820","https://openalex.org/W1608791393","https://openalex.org/W1807888379","https://openalex.org/W1856955241","https://openalex.org/W1859772613","https://openalex.org/W1918470385","https://openalex.org/W1935825130","https://openalex.org/W1956559956","https://openalex.org/W1966982551","https://openalex.org/W1977016445","https://openalex.org/W1984566373","https://openalex.org/W2008896880","https://openalex.org/W2071047814","https://openalex.org/W2086980839","https://openalex.org/W2095293504","https://openalex.org/W2112642935","https://openalex.org/W2138105615","https://openalex.org/W2138745488","https://openalex.org/W2140190241","https://openalex.org/W2140609014","https://openalex.org/W2140809065","https://openalex.org/W2149770511","https://openalex.org/W2150365753","https://openalex.org/W2160484893","https://openalex.org/W2168846860","https://openalex.org/W2169807577","https://openalex.org/W2171707538","https://openalex.org/W2220207089","https://openalex.org/W2294859229","https://openalex.org/W2295351501","https://openalex.org/W2400496014","https://openalex.org/W3004104752","https://openalex.org/W6607962253","https://openalex.org/W6634702315","https://openalex.org/W6640862754","https://openalex.org/W6680704940","https://openalex.org/W6684675310"],"related_works":["https://openalex.org/W2105333333","https://openalex.org/W2153455914","https://openalex.org/W1502610062","https://openalex.org/W1501673548","https://openalex.org/W1512562726","https://openalex.org/W2027162968","https://openalex.org/W2129469317","https://openalex.org/W1533863182","https://openalex.org/W2607324466","https://openalex.org/W2140379930"],"abstract_inverted_index":{"The":[0],"increasing":[1],"complexity":[2],"of":[3,10,39,48,52,89,96,104,157,201],"enterprise":[4],"databases":[5,53,188],"and":[6,18,28,58,82,109,130,142,170,189],"the":[7,20,46,121,178],"prevalent":[8],"lack":[9],"documentation":[11],"incur":[12],"significant":[13],"cost":[14],"in":[15,79],"both":[16],"understanding":[17],"integrating":[19],"databases.":[21,40],"Existing":[22],"solutions":[23],"addressed":[24],"mining":[25],"for":[26],"keys":[27],"foreign":[29],"keys,":[30],"but":[31],"paid":[32],"little":[33],"attention":[34],"to":[35,54,85,99,146,150],"more":[36],"high-level":[37],"structures":[38,51,196],"In":[41],"this":[42],"paper,":[43],"we":[44,123],"consider":[45],"problem":[47],"discovering":[49,147],"topical":[50,102,195],"support":[55],"semantic":[56,152],"browsing":[57],"large-scale":[59],"data":[60],"integration.":[61],"We":[62,134,180],"describe":[63],"iDisc,":[64],"a":[65,71,94,136,198],"novel":[66,127],"discovery":[67],"system":[68],"based":[69],"on":[70,139],"multi-strategy":[72],"learning":[73],"framework.":[74,179],"iDisc":[75,125,184],"exploits":[76],"varied":[77],"evidence":[78],"database":[80,90,107,168],"schema":[81],"instance":[83],"values":[84],"construct":[86],"multiple":[87],"kinds":[88],"representations.":[91],"It":[92],"employs":[93],"set":[95],"base":[97,171],"clusterers":[98,172],"discover":[100],"preliminary":[101],"clusters":[103,115],"tables":[105],"from":[106],"representations,":[108],"then":[110],"aggregate":[111],"them":[112],"into":[113,177],"final":[114],"via":[116],"meta-clustering.":[117],"To":[118],"further":[119],"improve":[120],"accuracy,":[122],"extend":[124],"with":[126,197],"multiple-level":[128],"aggregation":[129],"clusterer":[131],"boosting":[132],"techniques.":[133],"introduce":[135],"new":[137],"measure":[138],"table":[140],"importance":[141],"propose":[143],"an":[144],"approach":[145],"cluster":[148],"representatives":[149],"facilitate":[151],"browsing.":[153],"An":[154],"important":[155],"feature":[156],"our":[158],"framework":[159],"is":[160,163],"that":[161,192],"it":[162,193],"highly":[164],"extensible,":[165],"where":[166],"additional":[167],"representations":[169],"may":[173],"be":[174],"easily":[175],"incorporated":[176],"have":[181],"extensively":[182],"evaluated":[183],"using":[185],"large":[186],"real-world":[187],"results":[190],"show":[191],"discovers":[194],"high":[199],"degree":[200],"accuracy.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}