{"id":"https://openalex.org/W2434390175","doi":"https://doi.org/10.1145/2882903.2882924","title":"Automatic Generation of Normalized Relational Schemas from Nested Key-Value Data","display_name":"Automatic Generation of Normalized Relational Schemas from Nested Key-Value Data","publication_year":2016,"publication_date":"2016-06-14","ids":{"openalex":"https://openalex.org/W2434390175","doi":"https://doi.org/10.1145/2882903.2882924","mag":"2434390175"},"language":"en","primary_location":{"id":"doi:10.1145/2882903.2882924","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2882924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-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/A5053524949","display_name":"Michael DiScala","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael DiScala","raw_affiliation_strings":["Yale University, New Haven, CT, USA"],"affiliations":[{"raw_affiliation_string":"Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049333271","display_name":"Daniel J. Abadi","orcid":"https://orcid.org/0000-0003-3771-2995"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel J. Abadi","raw_affiliation_strings":["Yale University, New Haven, CT, USA"],"affiliations":[{"raw_affiliation_string":"Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053524949"],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":null,"apc_paid":null,"fwci":7.8175,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.9752701,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"295","last_page":"310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998000264167786,"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/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.8274533748626709},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.6712603569030762},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.5816449522972107},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5234037041664124},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.517727792263031},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5003185272216797},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4900881052017212},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.48827481269836426},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47438767552375793},{"id":"https://openalex.org/keywords/nosql","display_name":"NoSQL","score":0.4476538896560669},{"id":"https://openalex.org/keywords/relational-database-management-system","display_name":"Relational database management system","score":0.4400756061077118},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.396760493516922},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3908032178878784},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38862642645835876},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3629811406135559},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.3512091636657715},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.24092158675193787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8274533748626709},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.6712603569030762},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.5816449522972107},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5234037041664124},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.517727792263031},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5003185272216797},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4900881052017212},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.48827481269836426},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47438767552375793},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.4476538896560669},{"id":"https://openalex.org/C24394798","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database management system","level":3,"score":0.4400756061077118},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.396760493516922},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3908032178878784},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38862642645835876},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3629811406135559},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.3512091636657715},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.24092158675193787},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2882903.2882924","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2882924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1426690399","https://openalex.org/W1483940063","https://openalex.org/W1507976212","https://openalex.org/W1744189505","https://openalex.org/W1881756506","https://openalex.org/W1972386298","https://openalex.org/W1973440079","https://openalex.org/W1983428002","https://openalex.org/W1994962776","https://openalex.org/W2008896880","https://openalex.org/W2009758120","https://openalex.org/W2011716962","https://openalex.org/W2015071642","https://openalex.org/W2039610696","https://openalex.org/W2077053297","https://openalex.org/W2102489964","https://openalex.org/W2104476081","https://openalex.org/W2108014443","https://openalex.org/W2116493296","https://openalex.org/W2124654683","https://openalex.org/W2138745488","https://openalex.org/W2154784170","https://openalex.org/W2161938331","https://openalex.org/W2165286227","https://openalex.org/W2166194842","https://openalex.org/W2166549982","https://openalex.org/W2181714304","https://openalex.org/W2280869227","https://openalex.org/W4233419801","https://openalex.org/W4248809068","https://openalex.org/W6628575224","https://openalex.org/W6678679552","https://openalex.org/W6836815192"],"related_works":["https://openalex.org/W3027072330","https://openalex.org/W3127890688","https://openalex.org/W2904616523","https://openalex.org/W2295775753","https://openalex.org/W4381416854","https://openalex.org/W2603313942","https://openalex.org/W4306877231","https://openalex.org/W2143602713","https://openalex.org/W4386408829","https://openalex.org/W32424336"],"abstract_inverted_index":{"Self-describing":[0],"key-value":[1],"data":[2,41,59,87,92],"formats":[3],"such":[4,31,91],"as":[5,11,32,66],"JSON":[6],"are":[7],"becoming":[8],"increasingly":[9],"popular":[10],"application":[12],"developers":[13,77],"choose":[14],"to":[15,36,62],"avoid":[16],"the":[17,21,80,83,105,112],"rigidity":[18],"imposed":[19],"by":[20],"relational":[22],"model.":[23],"Database":[24],"systems":[25],"designed":[26],"for":[27],"these":[28],"self-describing":[29],"formats,":[30],"MongoDB,":[33],"encourage":[34],"users":[35],"use":[37],"denormalized,":[38],"heavily":[39],"nested":[40],"models":[42,60],"so":[43],"that":[44],"relationships":[45],"across":[46],"records":[47],"and":[48,72,98,107],"other":[49],"schema":[50],"information":[51],"need":[52],"not":[53],"be":[54],"predefined":[55],"or":[56],"standardized.":[57],"Such":[58],"contribute":[61],"long-term":[63],"development":[64],"complexity,":[65],"their":[67],"lack":[68],"of":[69,86,109],"explicit":[70],"entity":[71],"relationship":[73],"tracking":[74],"burdens":[75],"new":[76],"unfamiliar":[78],"with":[79],"dataset.":[81],"Furthermore,":[82],"large":[84],"amount":[85],"repetition":[88],"present":[89],"in":[90],"layouts":[93],"can":[94],"introduce":[95],"update":[96],"anomalies":[97],"poor":[99],"scan":[100],"performance,":[101],"which":[102],"reduce":[103],"both":[104],"quality":[106],"performance":[108],"analytics":[110],"over":[111],"data.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}