{"id":"https://openalex.org/W2948163032","doi":"https://doi.org/10.1145/3299869.3300065","title":"JOSIE","display_name":"JOSIE","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2948163032","doi":"https://doi.org/10.1145/3299869.3300065","mag":"2948163032"},"language":"en","primary_location":{"id":"doi:10.1145/3299869.3300065","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3299869.3300065","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3299869.3300065","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3299869.3300065","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013934423","display_name":"Erkang Zhu","orcid":"https://orcid.org/0009-0000-3326-1790"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Erkang Zhu","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103237059","display_name":"Dong Deng","orcid":"https://orcid.org/0000-0002-4596-3850"},"institutions":[{"id":"https://openalex.org/I4210116052","display_name":"Inception Institute of Artificial Intelligence","ror":"https://ror.org/02664zk40","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210116052"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Dong Deng","raw_affiliation_strings":["Rutgers University & Inception Institute of Artificial Intelligence, Abu Dhabi, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University & Inception Institute of Artificial Intelligence, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210116052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012572863","display_name":"Fatemeh Nargesian","orcid":"https://orcid.org/0000-0002-4710-8719"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fatemeh Nargesian","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022619313","display_name":"Ren\u00e9e J. Miller","orcid":"https://orcid.org/0000-0002-1484-4787"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ren\u00e9e J. Miller","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.8501,"has_fulltext":true,"cited_by_count":118,"citation_normalized_percentile":{"value":0.97969114,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"847","last_page":"864"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9994999766349792,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6592457890510559},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.6457663774490356},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.5520475506782532},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5430279970169067},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.5397485494613647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5232954621315002},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5071985721588135},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.47919735312461853},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45137161016464233},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4270949959754944},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3580474257469177},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33739495277404785},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.2358035445213318},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.22446441650390625},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.19348275661468506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18953514099121094},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14748883247375488},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08251982927322388}],"concepts":[{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6592457890510559},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.6457663774490356},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.5520475506782532},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5430279970169067},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.5397485494613647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5232954621315002},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5071985721588135},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.47919735312461853},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45137161016464233},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4270949959754944},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3580474257469177},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33739495277404785},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.2358035445213318},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.22446441650390625},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.19348275661468506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18953514099121094},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14748883247375488},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08251982927322388},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3299869.3300065","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3299869.3300065","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3299869.3300065","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3299869.3300065","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3299869.3300065","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3299869.3300065","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320312262","display_name":"Suncor Energy Incorporated","ror":"https://ror.org/02q291e51"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2948163032.pdf","grobid_xml":"https://content.openalex.org/works/W2948163032.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1455310343","https://openalex.org/W1532325895","https://openalex.org/W1536525420","https://openalex.org/W1721994796","https://openalex.org/W1969621019","https://openalex.org/W1973001156","https://openalex.org/W2001700730","https://openalex.org/W2073329022","https://openalex.org/W2093050254","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2104599107","https://openalex.org/W2105436061","https://openalex.org/W2108223890","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2130825214","https://openalex.org/W2132069633","https://openalex.org/W2151930506","https://openalex.org/W2167847032","https://openalex.org/W2270660075","https://openalex.org/W2286724461","https://openalex.org/W2341748398","https://openalex.org/W2396588571","https://openalex.org/W2585438896","https://openalex.org/W2606791715","https://openalex.org/W2616120155","https://openalex.org/W2619410666","https://openalex.org/W2752618741","https://openalex.org/W2795089200","https://openalex.org/W2798664493","https://openalex.org/W2883952940","https://openalex.org/W2963174348","https://openalex.org/W4213009331"],"related_works":["https://openalex.org/W2124379162","https://openalex.org/W2805651586","https://openalex.org/W2906958661","https://openalex.org/W2132792521","https://openalex.org/W2171572695","https://openalex.org/W2039742379","https://openalex.org/W2295679435","https://openalex.org/W2001669800","https://openalex.org/W2980679393","https://openalex.org/W2319176622"],"abstract_inverted_index":{"We":[0,124,180],"present":[1],"a":[2,14,121],"new":[3,156,209],"solution":[4],"for":[5,82],"finding":[6,176],"joinable":[7],"tables":[8,21],"in":[9,67,102,116,175,219],"massive":[10,132],"data":[11,128,195,225],"lakes:":[12],"given":[13,28],"table":[15,29],"and":[16,54,83,98,145,170,205,217],"one":[17],"join":[18],"column,":[19],"find":[20],"that":[22,126,139,147,182,207],"can":[23,39],"be":[24,40,141],"joined":[25],"with":[26,106],"the":[27,31,68,78,103,165,177,187],"on":[30,194,223],"largest":[32],"number":[33,112],"of":[34,70,87,113,143,150,152,167],"distinct":[35,114,153],"values.":[36,154],"The":[37],"problem":[38,48],"formulated":[41],"as":[42,52,57,215],"an":[43],"overlap":[44,189],"set":[45,62,92,100,133,137,168,190],"similarity":[46,63,191],"search":[47,64,73,192,211],"by":[49],"considering":[50],"columns":[51],"sets":[53,86,118],"matching":[55],"values":[56,115],"intersection":[58],"between":[59],"sets.":[60,179],"Although":[61],"is":[65,119],"well-studied":[66],"field":[69],"approximate":[71,203],"string":[72],"(e.g.,":[74],"fuzzy":[75],"keyword":[76],"search),":[77],"solutions":[79],"are":[80],"designed":[81],"evaluated":[84],"over":[85,96],"relatively":[88],"small":[89],"size":[90,93,101],"(average":[91],"rarely":[94],"much":[95],"100":[97],"maximum":[99,136],"low":[104],"thousands)":[105],"modest":[107],"dictionary":[108],"sizes":[109,134,138],"(the":[110],"total":[111],"all":[117],"only":[120],"few":[122],"million).":[123],"observe":[125],"modern":[127],"lakes":[129],"typically":[130],"have":[131],"(with":[135],"may":[140],"tens":[142],"millions)":[144],"dictionaries":[146],"include":[148],"hundreds":[149],"millions":[151],"Our":[155],"algorithm,":[157],"JOSIE":[158,183],"(Joining":[159],"Search":[160],"using":[161],"Intersection":[162],"Estimation)":[163],"minimizes":[164],"cost":[166],"reads":[169],"inverted":[171],"index":[172],"probes":[173],"used":[174],"top-k":[178],"show":[181,206],"completely":[184],"out":[185],"performs":[186,213],"state-of-the-art":[188,202],"techniques":[193],"lakes.":[196,226],"More":[197],"surprising,":[198],"we":[199],"also":[200],"consider":[201],"algorithm":[204,212],"our":[208],"exact":[210],"almost":[214],"well,":[216],"even":[218],"some":[220],"cases":[221],"better,":[222],"real":[224]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2019-06-14T00:00:00"}