{"id":"https://openalex.org/W3132781388","doi":"https://doi.org/10.14778/3447689.3447703","title":"Glean","display_name":"Glean","publication_year":2021,"publication_date":"2021-02-01","ids":{"openalex":"https://openalex.org/W3132781388","doi":"https://doi.org/10.14778/3447689.3447703","mag":"3132781388"},"language":"en","primary_location":{"id":"doi:10.14778/3447689.3447703","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3447689.3447703","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/A5102945075","display_name":"Sandeep Tata","orcid":"https://orcid.org/0009-0007-7785-5516"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandeep Tata","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065871791","display_name":"Navneet Potti","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Navneet Potti","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060825780","display_name":"James B. Wendt","orcid":"https://orcid.org/0000-0003-4980-5152"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James B. Wendt","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039915362","display_name":"Lauro Beltr\u00e3o Costa","orcid":"https://orcid.org/0000-0003-2951-0752"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lauro Beltr\u00e3o Costa","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037200145","display_name":"Marc Najork","orcid":"https://orcid.org/0000-0003-1423-0854"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc Najork","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067625586","display_name":"Beliz Gunel","orcid":"https://orcid.org/0000-0003-2541-4157"},"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":"Beliz Gunel","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.387,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81183199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":"14","issue":"6","first_page":"997","last_page":"1005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9973999857902527,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9962999820709229,"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":0.8220585584640503},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6170049905776978},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4644823968410492},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.44510340690612793},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43919622898101807},{"id":"https://openalex.org/keywords/vendor","display_name":"Vendor","score":0.43796998262405396},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.37646931409835815},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3484981060028076},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32624149322509766},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18757188320159912}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8220585584640503},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6170049905776978},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4644823968410492},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.44510340690612793},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43919622898101807},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.43796998262405396},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37646931409835815},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3484981060028076},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32624149322509766},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18757188320159912},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3447689.3447703","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3447689.3447703","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":0.5099999904632568,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1531887935","https://openalex.org/W1566513354","https://openalex.org/W1973435495","https://openalex.org/W1973483159","https://openalex.org/W1976258225","https://openalex.org/W2135767707","https://openalex.org/W2157316480","https://openalex.org/W2169347997","https://openalex.org/W2585438896","https://openalex.org/W2604259521","https://openalex.org/W2767669124","https://openalex.org/W2769041395","https://openalex.org/W2891117443","https://openalex.org/W2892181857","https://openalex.org/W2896457183","https://openalex.org/W2948784110","https://openalex.org/W2949370368","https://openalex.org/W2959716049","https://openalex.org/W2965762238","https://openalex.org/W2972985407","https://openalex.org/W3013864782","https://openalex.org/W3034864438","https://openalex.org/W3122383744","https://openalex.org/W4292341621"],"related_works":["https://openalex.org/W4241876414","https://openalex.org/W1974777241","https://openalex.org/W2062343566","https://openalex.org/W2116350809","https://openalex.org/W2081035100","https://openalex.org/W3206324740","https://openalex.org/W2075040658","https://openalex.org/W2497175360","https://openalex.org/W2357241418","https://openalex.org/W2329452785"],"abstract_inverted_index":{"Extracting":[0],"structured":[1,101],"information":[2,102],"from":[3,60,103],"templatic":[4],"documents":[5,31,90,105],"is":[6,28,47,187,219],"an":[7],"important":[8,223],"problem":[9,46],"with":[10],"the":[11,114,129,140,194,200,216],"potential":[12],"to":[13,44,54,66,75,98,182],"automate":[14],"many":[15],"real-world":[16,171],"business":[17],"workflows":[18],"such":[19,30,57,208],"as":[20,58,222,224],"payment,":[21],"procurement,":[22],"and":[23,87,119,147,157],"payroll.":[24],"The":[25],"core":[26],"challenge":[27],"that":[29,49,92,107,151,175,186,206,213],"can":[32],"be":[33],"laid":[34],"out":[35],"in":[36],"virtually":[37],"infinitely":[38],"different":[39],"ways.":[40],"A":[41],"good":[42,227],"solution":[43],"this":[45,77,110],"one":[48],"generalizes":[50],"well":[51],"not":[52],"only":[53],"known":[55,62],"templates":[56],"invoices":[59],"a":[61,71,80,84,153,159,162,170,184,226],"vendor,":[63],"but":[64],"also":[65],"unseen":[67],"ones.":[68],"We":[69,204],"developed":[70],"system":[72],"called":[73],"Glean":[74,94],"tackle":[76],"problem.":[78],"Given":[79],"target":[81],"schema":[82],"for":[83,139,161,207],"document":[85,164],"type":[86],"some":[88],"labeled":[89,145],"of":[91,106,117,131],"type,":[93],"uses":[95],"machine":[96,141],"learning":[97,142],"automatically":[99],"extract":[100],"other":[104],"type.":[108,165],"In":[109],"paper,":[111],"we":[112,173,202],"describe":[113],"overall":[115],"architecture":[116,198],"Glean,":[118],"discuss":[120],"three":[121],"key":[122],"data":[123,138,177,218],"management":[124,178],"challenges":[125],":":[126],"1)":[127],"managing":[128],"quality":[130],"ground":[132],"truth":[133],"data,":[134],"2)":[135],"generating":[136],"training":[137,217],"model":[143,160,185,197,228],"using":[144],"documents,":[146],"3)":[148],"building":[149],"tools":[150],"help":[152],"developer":[154],"rapidly":[155],"build":[156],"improve":[158],"given":[163],"Through":[166],"empirical":[167],"studies":[168],"on":[169],"dataset,":[172],"show":[174],"these":[176],"techniques":[179,201],"allow":[180],"us":[181],"train":[183],"over":[188],"5":[189],"F1":[190],"points":[191],"better":[192],"than":[193],"exact":[195],"same":[196],"without":[199],"describe.":[203],"argue":[205],"information-extraction":[209],"problems,":[210],"designing":[211],"abstractions":[212],"carefully":[214],"manage":[215],"at":[220],"least":[221],"choosing":[225],"architecture.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2021-03-01T00:00:00"}