{"id":"https://openalex.org/W2009896441","doi":"https://doi.org/10.1145/1247480.1247637","title":"Information discovery in loosely integrated data","display_name":"Information discovery in loosely integrated data","publication_year":2007,"publication_date":"2007-06-11","ids":{"openalex":"https://openalex.org/W2009896441","doi":"https://doi.org/10.1145/1247480.1247637","mag":"2009896441"},"language":"en","primary_location":{"id":"doi:10.1145/1247480.1247637","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1247480.1247637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 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/A5026280956","display_name":"Heasoo Hwang","orcid":"https://orcid.org/0000-0002-3397-2303"},"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":"Heasoo Hwang","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003379355","display_name":"Andrey Balmin","orcid":"https://orcid.org/0000-0003-3034-6259"},"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":"Andrey Balmin","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083725187","display_name":"Hamid Pirahesh","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":"Hamid Pirahesh","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","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","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026280956"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":0.6485,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68037204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1147","last_page":"1149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9987000226974487,"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":0.9987000226974487,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9980000257492065,"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":0.8566789627075195},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6122786402702332},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5671880841255188},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5587561130523682},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5284514427185059},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5001640319824219},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.49310538172721863},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.4803232252597809},{"id":"https://openalex.org/keywords/graph-database","display_name":"Graph database","score":0.4688630700111389},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.46260297298431396},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4524660110473633},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4189724624156952},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.35040271282196045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8566789627075195},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6122786402702332},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5671880841255188},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5587561130523682},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5284514427185059},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5001640319824219},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.49310538172721863},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.4803232252597809},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.4688630700111389},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.46260297298431396},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4524660110473633},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4189724624156952},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.35040271282196045},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1247480.1247637","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1247480.1247637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.459.4822","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.459.4822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://mailserver.di.unipi.it/ricerca/proceedings/sigmod-pods2007/sigmod/p1147.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1525949272","https://openalex.org/W1539585011","https://openalex.org/W2168846860"],"related_works":["https://openalex.org/W2533706070","https://openalex.org/W2184474188","https://openalex.org/W3094024929","https://openalex.org/W2066869521","https://openalex.org/W2105258824","https://openalex.org/W3210975432","https://openalex.org/W2547614144","https://openalex.org/W2136530748","https://openalex.org/W2321599862","https://openalex.org/W1970380778"],"abstract_inverted_index":{"We":[0,63,87,104],"model":[1],"heterogeneous":[2],"data":[3,21,35,75,164],"sources":[4],"with":[5,20],"cross":[6],"references,":[7],"such":[8],"as":[9,16,23,30],"those":[10],"crawled":[11],"on":[12],"the":[13,33,65,71,82,89,94,100,132,142,157,162],"(enterprise)":[14],"web,":[15],"a":[17,85],"labeled":[18,34],"graph":[19],"objects":[22,55,76,79],"typed":[24],"nodes":[25,121,158],"and":[26,40,119,159],"references":[27],"or":[28],"links":[29,160],"edges.":[31],"Given":[32],"graph,":[36],"we":[37],"introduce":[38,64],"flexible":[39],"efficient":[41],"querying":[42],"capabilities":[43,48],"that":[44,56,69,98,115,122],"go":[45],"beyond":[46],"existing":[47],"by":[49],"additionally":[50],"discovering":[51],"meaningful":[52],"relationships":[53],"between":[54,74],"satisfy":[57],"keyword":[58],"and/or":[59],"structured":[60],"query":[61,113,139],"filters.":[62],"relationship":[66,90],"search":[67,91],"operator":[68,92],"exploits":[70],"link":[72],"structure":[73],"to":[77,81,126,141,149],"rank":[78],"related":[80],"result":[83,128],"of":[84,117,131],"filter.":[86],"implement":[88],"using":[93],"ObjectRank":[95],"[1]":[96],"algorithm":[97],"uses":[99],"random":[101],"surfer":[102],"model.":[103],"study":[105],"several":[106],"alternatives":[107],"for":[108,112,137],"constructing":[109],"summary":[110,133],"graphs":[111,134],"results":[114,140],"consist":[116],"individual":[118],"aggregate":[120],"are":[123,135],"somehow":[124],"linked":[125],"qualifying":[127],"nodes.":[129],"Some":[130],"useful":[136],"presenting":[138],"user,":[143],"while":[144],"others":[145],"could":[146],"be":[147],"used":[148],"evaluate":[150],"subsequent":[151],"queries":[152],"efficiently":[153],"without":[154],"considering":[155],"all":[156],"in":[161],"original":[163],"graph.":[165],"ACM":[166],"CLASSIFICATOIN":[167]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
