{"id":"https://openalex.org/W4402043058","doi":"https://doi.org/10.14778/3681954.3682019","title":"ReCG: Bottom-up JSON Schema Discovery Using a Repetitive Cluster-and-Generalize Framework","display_name":"ReCG: Bottom-up JSON Schema Discovery Using a Repetitive Cluster-and-Generalize Framework","publication_year":2024,"publication_date":"2024-07-01","ids":{"openalex":"https://openalex.org/W4402043058","doi":"https://doi.org/10.14778/3681954.3682019"},"language":"en","primary_location":{"id":"doi:10.14778/3681954.3682019","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3681954.3682019","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/A5114217257","display_name":"Joohyung Yun","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joohyung Yun","raw_affiliation_strings":["POSTECH, Pohang, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH, Pohang, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010776108","display_name":"Byungchul Tak","orcid":"https://orcid.org/0000-0002-8204-6816"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byungchul Tak","raw_affiliation_strings":["Kyungpook National University, Daegu, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyungpook National University, Daegu, Republic of Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035744252","display_name":"Wook-Shin Han","orcid":"https://orcid.org/0000-0001-9206-9563"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I2799891827","display_name":"Korea Post","ror":"https://ror.org/00p45d091","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799891827","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wook-Shin Han","raw_affiliation_strings":["Graduate School of AI, POSTECH, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of AI, POSTECH, Republic of Korea","institution_ids":["https://openalex.org/I2799891827","https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6109,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73570671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"17","issue":"11","first_page":"3538","last_page":"3550"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9990000128746033,"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":0.9990000128746033,"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/T11719","display_name":"Data Quality and Management","score":0.9976999759674072,"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":0.9958999752998352,"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/json","display_name":"JSON","score":0.97515469789505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8090382814407349},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5228424668312073},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.48895466327667236},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40146780014038086},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35862040519714355},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3506450057029724},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23207500576972961}],"concepts":[{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.97515469789505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8090382814407349},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5228424668312073},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.48895466327667236},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40146780014038086},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35862040519714355},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3506450057029724},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23207500576972961}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3681954.3682019","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3681954.3682019","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/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W199156438","https://openalex.org/W1508914815","https://openalex.org/W1575324001","https://openalex.org/W1987748328","https://openalex.org/W2036792013","https://openalex.org/W2054658115","https://openalex.org/W2134536645","https://openalex.org/W2160021452","https://openalex.org/W2169196165","https://openalex.org/W2181714304","https://openalex.org/W2265048516","https://openalex.org/W2341844252","https://openalex.org/W2569219525","https://openalex.org/W2574472735","https://openalex.org/W2619959750","https://openalex.org/W2734941459","https://openalex.org/W2752005949","https://openalex.org/W2793317603","https://openalex.org/W2798777841","https://openalex.org/W2887418847","https://openalex.org/W2907544011","https://openalex.org/W2948974967","https://openalex.org/W2963114528","https://openalex.org/W2980426319","https://openalex.org/W3014023550","https://openalex.org/W3099713549","https://openalex.org/W3131359276","https://openalex.org/W3173993340","https://openalex.org/W3174369108","https://openalex.org/W4214810323","https://openalex.org/W4248809068","https://openalex.org/W4281720128","https://openalex.org/W4297970464","https://openalex.org/W4303984359","https://openalex.org/W4384659457","https://openalex.org/W4390603329","https://openalex.org/W6630579097","https://openalex.org/W6683105740","https://openalex.org/W6727233892"],"related_works":["https://openalex.org/W2753132265","https://openalex.org/W4234766820","https://openalex.org/W4321232174","https://openalex.org/W3117520771","https://openalex.org/W2482048793","https://openalex.org/W4388027365","https://openalex.org/W2938860153","https://openalex.org/W4312551432","https://openalex.org/W2365783963","https://openalex.org/W2898214470"],"abstract_inverted_index":{"The":[0],"schemalessness,":[1],"one":[2,179],"of":[3,7,48,64,69,74,94,149,193],"the":[4,62,75,91,138,150,167,174,189,215],"major":[5],"advantages":[6],"JSON":[8,41,49,70,79,123,139],"representation":[9],"format,":[10],"comes":[11],"with":[12,180],"high":[13,198],"penalties":[14],"in":[15,103,125,137,202],"querying":[16],"and":[17,87,191],"operations":[18],"by":[19,196],"denying":[20],"various":[21],"critical":[22],"functions":[23],"such":[24,97],"as":[25,197,199],"query":[26],"optimizations,":[27],"indexing,":[28],"or":[29],"data":[30],"verification.":[31],"There":[32],"have":[33],"been":[34],"continuous":[35],"efforts":[36],"to":[37,84,89,109,169],"develop":[38],"an":[39,117],"accurate":[40,178],"schema":[42,53,92,151],"discovery":[43,54],"algorithm":[44],"from":[45,61,133],"a":[46,126],"bag":[47],"documents.":[50],"Unfortunately,":[51],"existing":[52],"techniques,":[55],"being":[56],"top-down":[57,81,107],"algorithms,":[58],"face":[59],"challenges":[60],"lack":[63],"visibility":[65],"into":[66],"children":[67],"nodes":[68],"tree.":[71],"With":[72],"absence":[73],"information":[76],"about":[77],"lower-level":[78],"elements,":[80],"algorithms":[82,108],"need":[83],"employ":[85],"assumptions":[86],"heuristics":[88],"decide":[90],"type":[93],"nodes.":[95],"However,":[96],"static":[98],"decisions":[99,148],"are":[100],"often":[101],"violated":[102],"datasets":[104],"which":[105],"causes":[106],"perform":[110],"poorly.":[111],"To":[112],"overcome":[113],"this,":[114],"we":[115,156],"propose":[116],"algorithm,":[118],"called":[119],"ReCG,":[120],"that":[121,185],"processes":[122],"documents":[124],"bottom-up":[127],"manner.":[128],"It":[129],"builds":[130],"up":[131,166],"schemas":[132,168,173,195],"leaf":[134],"elements":[135],"upward":[136],"document":[140],"tree":[141],"and,":[142],"thus,":[143],"can":[144],"make":[145],"more":[146],"informed":[147],"node":[152],"types.":[153],"In":[154],"addition,":[155],"adopt":[157],"MDL":[158],"(Minimum":[159],"Description":[160],"Length)":[161],"principles":[162],"systematically":[163],"while":[164,207],"building":[165],"choose":[170],"among":[171],"candidate":[172],"most":[175],"concise":[176],"yet":[177],"well-balanced":[181],"generality.":[182],"Evaluations":[183],"show":[184],"our":[186],"technique":[187],"improves":[188],"recall":[190],"precision":[192],"found":[194],"47%,":[200],"resulting":[201],"46%":[203],"better":[204],"F1":[205],"score":[206],"also":[208],"performing":[209],"2.11\u00d7":[210],"faster":[211],"on":[212],"average":[213],"against":[214],"state-of-the-art.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}