{"id":"https://openalex.org/W2122483056","doi":"https://doi.org/10.14778/1453856.1453941","title":"Learning to create data-integrating queries","display_name":"Learning to create data-integrating queries","publication_year":2008,"publication_date":"2008-08-01","ids":{"openalex":"https://openalex.org/W2122483056","doi":"https://doi.org/10.14778/1453856.1453941","mag":"2122483056"},"language":"en","primary_location":{"id":"doi:10.14778/1453856.1453941","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1453856.1453941","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5033696194","display_name":"Partha Talukdar","orcid":"https://orcid.org/0000-0001-8825-589X"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Partha Pratim Talukdar","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086888117","display_name":"Marie Jacob","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marie Jacob","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002598478","display_name":"Muhammad Salman Mehmood","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhammad Salman Mehmood","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006419939","display_name":"Koby Crammer","orcid":"https://orcid.org/0000-0001-8824-5747"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Koby Crammer","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063822723","display_name":"Zachary G. Ives","orcid":"https://orcid.org/0000-0001-7527-2957"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary G. Ives","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044708805","display_name":"Fernando Pereira","orcid":"https://orcid.org/0000-0001-6100-947X"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fernando Pereira","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114008024","display_name":"Sudipto Guha","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudipto Guha","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5033696194"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":21.1471,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.9939069,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"1","issue":"1","first_page":"785","last_page":"796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9973999857902527,"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":0.996999979019165,"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":0.8363311886787415},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6207278370857239},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5724809765815735},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4338076710700989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363311886787415},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6207278370857239},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5724809765815735},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4338076710700989}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.14778/1453856.1453941","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1453856.1453941","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.140.8865","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.140.8865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/1/1453941.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.141.6114","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.6114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.upenn.edu/~zives/research/kbdi.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.145.6225","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.145.6225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.upenn.edu/~sudipto/mypapers/kbdi.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.145.6969","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.145.6969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.upenn.edu/~partha/papers/kbdi_final.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":51,"referenced_works":["https://openalex.org/W194033037","https://openalex.org/W1483411935","https://openalex.org/W1519573073","https://openalex.org/W1539585011","https://openalex.org/W1552694902","https://openalex.org/W1597031998","https://openalex.org/W1660390307","https://openalex.org/W1781113593","https://openalex.org/W1967053016","https://openalex.org/W1971676915","https://openalex.org/W1973828215","https://openalex.org/W1984407615","https://openalex.org/W2008896880","https://openalex.org/W2011039300","https://openalex.org/W2011282943","https://openalex.org/W2020586530","https://openalex.org/W2038281398","https://openalex.org/W2063395464","https://openalex.org/W2068362339","https://openalex.org/W2078686663","https://openalex.org/W2084538728","https://openalex.org/W2084987750","https://openalex.org/W2086240273","https://openalex.org/W2098388305","https://openalex.org/W2098571317","https://openalex.org/W2099797738","https://openalex.org/W2100408869","https://openalex.org/W2107105629","https://openalex.org/W2108991785","https://openalex.org/W2113970290","https://openalex.org/W2116544254","https://openalex.org/W2123390832","https://openalex.org/W2125332694","https://openalex.org/W2128964720","https://openalex.org/W2154268919","https://openalex.org/W2160218441","https://openalex.org/W2161569281","https://openalex.org/W2169624745","https://openalex.org/W2171874178","https://openalex.org/W2172222998","https://openalex.org/W2201552871","https://openalex.org/W2293299776","https://openalex.org/W2336259629","https://openalex.org/W3009009611","https://openalex.org/W3148632216","https://openalex.org/W4232413872","https://openalex.org/W4242645045","https://openalex.org/W4253103473","https://openalex.org/W6635649160","https://openalex.org/W6637101025","https://openalex.org/W6678380215"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"The":[0,53,161],"number":[1],"of":[2,36,55,92,179,202,251,280,291],"potentially-related":[3],"data":[4,11,40,241],"resources":[5,41],"available":[6,43],"for":[7],"querying":[8],"---":[9,16],"databases,":[10],"warehouses,":[12],"virtual":[13],"integrated":[14],"schemas":[15,54],"continues":[17],"to":[18,68,103,117,152,190,198,206,233,260,263,268,284],"grow":[19],"rapidly.":[20],"Perhaps":[21],"no":[22],"area":[23],"has":[24],"seen":[25],"this":[26,234],"problem":[27],"as":[28,30,274],"acutely":[29],"the":[31,81,90,105,175,196,200,212,228,231,244,249,252,256,269,278,281,289,303],"life":[32],"sciences,":[33],"where":[34],"hundreds":[35],"large,":[37],"complex,":[38],"interlinked":[39],"are":[42,58,83,112,128,167,236],"on":[44,61,89,248],"fields":[45],"like":[46],"proteomics,":[47],"genomics,":[48],"disease":[49],"studies,":[50],"and":[51,77,96,121,131,149,172,188,214,238,243,265,301],"pharmacology.":[52],"individual":[56],"databases":[57],"often":[59,115,129],"large":[60],"their":[62,173],"own,":[63],"but":[64],"users":[65,82],"also":[66],"need":[67],"pose":[69,220],"queries":[70,165,194,203,222,282],"across":[71],"multiple":[72,133,192],"sources,":[73],"exploiting":[74],"foreign":[75,182],"keys":[76],"schema":[78,185],"mappings.":[79],"Since":[80],"not":[84],"experts,":[85],"they":[86],"typically":[87],"rely":[88],"existence":[91],"pre-defined":[93],"Web":[94,150,208],"forms":[95,111],"associated":[97],"query":[98,147,209,235],"templates,":[99],"developed":[100],"by":[101,155,223],"programmers":[102],"meet":[104],"particular":[106],"scientists'":[107],"needs.":[108,160],"Unfortunately,":[109],"such":[110],"scarce":[113],"commodities,":[114],"limited":[116],"a":[118,137,141,207,275],"single":[119],"database,":[120],"mismatched":[122],"with":[123,139,157,240],"biologists'":[124],"information":[125,159,272],"needs":[126],"that":[127,166],"context-sensitive":[130],"span":[132],"databases.":[134],"We":[135,287],"present":[136],"system":[138,176,257],"which":[140,255],"non-expert":[142],"user":[143,162,213,245],"can":[144],"author":[145],"new":[146],"templates":[148],"forms,":[151],"be":[153],"reused":[154],"anyone":[156],"related":[158],"poses":[163],"keyword":[164],"matched":[168],"against":[169,294],"source":[170],"relations":[171],"attributes;":[174],"uses":[177],"sequences":[178],"associations":[180,266],"(e.g.,":[181],"keys,":[183],"links,":[184],"mappings,":[186],"synonyms,":[187],"taxonomies)":[189],"create":[191],"ranked":[193,237],"linking":[195],"matches":[197],"keywords;":[199],"set":[201],"is":[204],"attached":[205],"form.":[210,229],"Now":[211],"his":[215],"or":[216],"her":[217],"associates":[218],"may":[219],"specific":[221,271],"filling":[224],"in":[225,227],"parameters":[226],"Importantly,":[230],"answers":[232],"annotated":[239],"provenance,":[242],"provides":[246],"feedback":[247],"utility":[250],"answers,":[253],"from":[254,298],"ultimately":[258],"learns":[259],"assign":[261],"costs":[262,297],"sources":[264],"according":[267],"user's":[270],"need,":[273],"result":[276],"changing":[277],"ranking":[279],"used":[283],"generate":[285],"results.":[286],"evaluate":[288],"effectiveness":[290],"our":[292],"method":[293],"\"gold":[295],"standard\"":[296],"domain":[299],"experts":[300],"demonstrate":[302],"method's":[304],"scalability.":[305]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":11}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}