{"id":"https://openalex.org/W4321448337","doi":"https://doi.org/10.14778/3574245.3574274","title":"Integrating Data Lake Tables","display_name":"Integrating Data Lake Tables","publication_year":2022,"publication_date":"2022-12-01","ids":{"openalex":"https://openalex.org/W4321448337","doi":"https://doi.org/10.14778/3574245.3574274"},"language":"en","primary_location":{"id":"doi:10.14778/3574245.3574274","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3574245.3574274","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/A5047161025","display_name":"Aamod Khatiwada","orcid":"https://orcid.org/0000-0001-5720-1207"},"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":true,"raw_author_name":"Aamod Khatiwada","raw_affiliation_strings":["Northeastern University, Boston, Massachusetts, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, Massachusetts, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002899918","display_name":"Roee Shraga","orcid":"https://orcid.org/0000-0001-8803-8481"},"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":"Roee Shraga","raw_affiliation_strings":["Northeastern University, Boston, Massachusetts, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, Massachusetts, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086781628","display_name":"Wolfgang Gatterbauer","orcid":"https://orcid.org/0000-0002-9614-0504"},"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":"Wolfgang Gatterbauer","raw_affiliation_strings":["Northeastern University, Boston, Massachusetts, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, Massachusetts, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"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, Massachusetts, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, Massachusetts, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047161025"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":6.4278,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.97199974,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"16","issue":"4","first_page":"932","last_page":"945"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9954000115394592,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9948999881744385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6430891752243042},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.640216588973999},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.569442093372345},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.5516904592514038},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5117754340171814},{"id":"https://openalex.org/keywords/null","display_name":"Null (SQL)","score":0.510572075843811},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.46859851479530334},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.46274545788764954},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36283957958221436},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2236258089542389},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15693992376327515},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15081247687339783}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6430891752243042},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.640216588973999},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.569442093372345},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5516904592514038},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5117754340171814},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.510572075843811},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46859851479530334},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.46274545788764954},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36283957958221436},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2236258089542389},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15693992376327515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15081247687339783},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3574245.3574274","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3574245.3574274","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W180578187","https://openalex.org/W259507342","https://openalex.org/W1965761777","https://openalex.org/W1981590391","https://openalex.org/W1987971958","https://openalex.org/W2008896880","https://openalex.org/W2051224630","https://openalex.org/W2085487226","https://openalex.org/W2111162011","https://openalex.org/W2111869785","https://openalex.org/W2122789628","https://openalex.org/W2139450862","https://openalex.org/W2140116426","https://openalex.org/W2156247618","https://openalex.org/W2189625117","https://openalex.org/W2295240344","https://openalex.org/W2337288897","https://openalex.org/W2405849109","https://openalex.org/W2616147950","https://openalex.org/W2750991217","https://openalex.org/W2752618741","https://openalex.org/W2798664493","https://openalex.org/W2810039498","https://openalex.org/W2889003264","https://openalex.org/W2961334167","https://openalex.org/W2970992672","https://openalex.org/W2997591727","https://openalex.org/W2997991760","https://openalex.org/W3037878364","https://openalex.org/W3196867679","https://openalex.org/W4236940322","https://openalex.org/W4244075691","https://openalex.org/W4255392906","https://openalex.org/W4301104863","https://openalex.org/W4303449483","https://openalex.org/W4391156274"],"related_works":["https://openalex.org/W3214148052","https://openalex.org/W2151692181","https://openalex.org/W794462722","https://openalex.org/W2029625042","https://openalex.org/W4248476017","https://openalex.org/W2807741550","https://openalex.org/W2964879389","https://openalex.org/W2970426051","https://openalex.org/W1525319740","https://openalex.org/W4247864646"],"abstract_inverted_index":{"We":[0,64,87],"have":[1,77,123],"made":[2],"tremendous":[3],"strides":[4],"in":[5,42,51],"providing":[6],"tools":[7],"for":[8,16,35,54,70,96,137],"data":[9,55,62,142],"scientists":[10],"to":[11,57],"discover":[12],"new":[13,135],"tables":[14,28,59,74,106],"useful":[15],"their":[17],"analyses.":[18],"But":[19],"despite":[20],"these":[21],"advances,":[22],"the":[23,43,67,98,114],"proper":[24],"integration":[25,72,138],"of":[26,73],"discovered":[27,79],"has":[29,47],"been":[30,48,78],"under-explored.":[31],"An":[32],"interesting":[33],"semantics":[34],"integration,":[36],"called":[37],"Full":[38,99],"Disjunction,":[39],"was":[40],"proposed":[41],"1980's,":[44],"but":[45],"there":[46],"little":[49],"progress":[50],"using":[52,80],"it":[53],"science":[56],"integrate":[58],"culled":[60],"from":[61],"lakes.":[63],"provide":[65],"ALITE,":[66,129],"first":[68],"proposal":[69],"scalable":[71],"that":[75,90,105,139],"may":[76],"join,":[81],"union":[82],"or":[83],"related":[84],"table":[85],"search.":[86],"empirically":[88],"show":[89],"ALITE":[91,101],"can":[92],"outperform":[93],"previous":[94,103],"algorithms":[95],"computing":[97],"Disjunction.":[100],"relaxes":[102],"assumptions":[104],"share":[107,133],"common":[108],"attribute":[109],"names":[110],"(which":[111],"completely":[112],"determine":[113],"join":[115,125],"columns),":[116],"are":[117],"complete":[118],"(without":[119],"null":[120],"values),":[121],"and":[122,132],"acyclic":[124],"patterns.":[126],"To":[127],"evaluate":[128],"we":[130],"develop":[131],"three":[134],"benchmarks":[136],"use":[140],"real":[141],"lake":[143],"tables.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":9},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}
