{"id":"https://openalex.org/W4285335450","doi":"https://doi.org/10.14778/3494124.3494149","title":"Ember","display_name":"Ember","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W4285335450","doi":"https://doi.org/10.14778/3494124.3494149"},"language":"en","primary_location":{"id":"doi:10.14778/3494124.3494149","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3494124.3494149","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/A5057132920","display_name":"Sahaana Suri","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sahaana Suri","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000141065","display_name":"Ihab F. Ilyas","orcid":"https://orcid.org/0000-0001-9052-9714"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ihab F. Ilyas","raw_affiliation_strings":["University of Waterloo"],"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109519525","display_name":"Christopher R\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher R\u00e9","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002060759","display_name":"Theodoros Rekatsinas","orcid":"https://orcid.org/0000-0001-6148-1854"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Theodoros Rekatsinas","raw_affiliation_strings":["UW-Madison"],"affiliations":[{"raw_affiliation_string":"UW-Madison","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057132920"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.3942,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.82604483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"15","issue":"3","first_page":"699","last_page":"712"},"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9965000152587891,"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":0.7900516986846924},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.7194573283195496},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5963523387908936},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4305551052093506},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42089781165122986},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3604785203933716},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34796303510665894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3428041934967041},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.34195324778556824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900516986846924},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7194573283195496},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5963523387908936},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4305551052093506},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42089781165122986},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3604785203933716},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34796303510665894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3428041934967041},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34195324778556824},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3494124.3494149","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3494124.3494149","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":[{"id":"https://metadata.un.org/sdg/9","score":0.5699999928474426,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1964189668","https://openalex.org/W1987308036","https://openalex.org/W2030808931","https://openalex.org/W2104511295","https://openalex.org/W2106053110","https://openalex.org/W2125980212","https://openalex.org/W2137435551","https://openalex.org/W2140116426","https://openalex.org/W2156037541","https://openalex.org/W2269738476","https://openalex.org/W2286724461","https://openalex.org/W2438792749","https://openalex.org/W2444650685","https://openalex.org/W2542998387","https://openalex.org/W2610871042","https://openalex.org/W2613536717","https://openalex.org/W2648699835","https://openalex.org/W2769041395","https://openalex.org/W2771472444","https://openalex.org/W2795089200","https://openalex.org/W2798649495","https://openalex.org/W2895361760","https://openalex.org/W2896457183","https://openalex.org/W2957204582","https://openalex.org/W2959716049","https://openalex.org/W2963563276","https://openalex.org/W2970204018","https://openalex.org/W2979826702","https://openalex.org/W2992897306","https://openalex.org/W3014295153","https://openalex.org/W3014705052","https://openalex.org/W3016010032","https://openalex.org/W3021397474","https://openalex.org/W3035231859","https://openalex.org/W3037852608","https://openalex.org/W3081323384","https://openalex.org/W3099734810","https://openalex.org/W3123375411","https://openalex.org/W3124503495","https://openalex.org/W3170190513","https://openalex.org/W3197468999"],"related_works":["https://openalex.org/W2088925915","https://openalex.org/W2382891957","https://openalex.org/W2393491644","https://openalex.org/W2067184662","https://openalex.org/W3047837489","https://openalex.org/W2622139626","https://openalex.org/W2133660117","https://openalex.org/W2104496206","https://openalex.org/W3013303285","https://openalex.org/W2385836742"],"abstract_inverted_index":{"Structured":[0],"data,":[1],"or":[2,26,40,50],"data":[3,60,84],"that":[4,75,96,110,150],"adheres":[5],"to":[6,102,154,175],"a":[7,17,94,114,182],"pre-defined":[8],"schema,":[9],"can":[10,20,112,170],"suffer":[11],"from":[12],"fragmented":[13,42],"context:":[14],"information":[15],"describing":[16],"single":[18,183],"entity":[19],"be":[21],"scattered":[22],"across":[23],"multiple":[24],"datasets":[25],"tables":[27],"tailored":[28],"for":[29,160],"specific":[30],"business":[31],"needs,":[32],"with":[33,124,178],"no":[34],"explicit":[35,51],"linking":[36],"keys.":[37],"Context":[38],"enrichment,":[39],"rebuilding":[41],"context,":[43],"using":[44,81],"keyless":[45,100,116],"joins":[46,101],"is":[47,64,109],"an":[48,121],"implicit":[49],"step":[52],"in":[53,70],"machine":[54],"learning":[55,135],"(ML)":[56],"pipelines":[57,80,159],"over":[58],"structured":[59],"sources.":[61],"This":[62],"process":[63],"tedious,":[65],"domain-specific,":[66],"and":[67,85,98,142,147,166,169],"lacks":[68],"support":[69],"now-prevalent":[71],"no-code":[72,156],"ML":[73,79],"systems":[74],"let":[76],"users":[77,153],"create":[78],"just":[82],"input":[83],"high-level":[86],"configuration":[87,185],"files.":[88],"In":[89],"response,":[90],"we":[91],"propose":[92],"Ember,":[93,146],"system":[95],"abstracts":[97],"automates":[99],"generalize":[103],"context":[104,157],"enrichment.":[105],"Our":[106],"key":[107],"insight":[108],"Ember":[111,127,151],"enable":[113],"general":[115],"join":[117],"operator":[118],"by":[119,131,173],"constructing":[120],"index":[122],"populated":[123],"task-specific":[125],"embeddings.":[126],"learns":[128],"these":[129],"embeddings":[130],"leveraging":[132],"Transformer-based":[133],"representation":[134],"techniques.":[136],"We":[137],"describe":[138],"our":[139],"architectural":[140],"principles":[141],"operators":[143],"when":[144],"developing":[145],"empirically":[148],"demonstrate":[149],"allows":[152],"develop":[155],"enrichment":[158],"five":[161],"domains,":[162],"including":[163],"search,":[164],"recommendation":[165],"question":[167],"answering,":[168],"exceed":[171],"alternatives":[172],"up":[174],"39%":[176],"recall,":[177],"as":[179,181],"little":[180],"line":[184],"change.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-07-14T00:00:00"}