{"id":"https://openalex.org/W4282592169","doi":"https://doi.org/10.1145/3514221.3526174","title":"Statistical Schema Learning with Occam's Razor","display_name":"Statistical Schema Learning with Occam's Razor","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4282592169","doi":"https://doi.org/10.1145/3514221.3526174"},"language":"en","primary_location":{"id":"doi:10.1145/3514221.3526174","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3526174","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 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/A5073731680","display_name":"Justin Talbot","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Justin Talbot","raw_affiliation_strings":["Databricks, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Databricks, San Francisco, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090993570","display_name":"Daniel Ting","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163771","display_name":"Tableau Software (United States)","ror":"https://ror.org/053v5e348","country_code":"US","type":"company","lineage":["https://openalex.org/I4210163771"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Ting","raw_affiliation_strings":["Tableau Research, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tableau Research, Seattle, WA, USA","institution_ids":["https://openalex.org/I4210163771"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073731680"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06588109,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"176","last_page":"189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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":0.9939000010490417,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9937999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.820944607257843},{"id":"https://openalex.org/keywords/occam","display_name":"occam","score":0.7798900604248047},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7351651191711426},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6111181974411011},{"id":"https://openalex.org/keywords/occams-razor","display_name":"Occam's razor","score":0.5570703148841858},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.4804213047027588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4589124917984009},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4125775396823883},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37557005882263184},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3601881265640259},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20017248392105103},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.09795156121253967},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0819670557975769}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820944607257843},{"id":"https://openalex.org/C78469957","wikidata":"https://www.wikidata.org/wiki/Q838062","display_name":"occam","level":2,"score":0.7798900604248047},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7351651191711426},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6111181974411011},{"id":"https://openalex.org/C64802038","wikidata":"https://www.wikidata.org/wiki/Q131012","display_name":"Occam's razor","level":2,"score":0.5570703148841858},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.4804213047027588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4589124917984009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4125775396823883},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37557005882263184},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3601881265640259},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20017248392105103},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.09795156121253967},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0819670557975769},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3514221.3526174","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3526174","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1881756506","https://openalex.org/W1994962776","https://openalex.org/W2023663289","https://openalex.org/W2028509346","https://openalex.org/W2135105491","https://openalex.org/W2140100614","https://openalex.org/W2140609014","https://openalex.org/W2148417962","https://openalex.org/W2163166770","https://openalex.org/W2166549982","https://openalex.org/W2232417456","https://openalex.org/W2247875277","https://openalex.org/W2281341896","https://openalex.org/W2439326083","https://openalex.org/W2612173678","https://openalex.org/W2618188015","https://openalex.org/W2803396353","https://openalex.org/W2891500072","https://openalex.org/W2952611840","https://openalex.org/W2964129930","https://openalex.org/W3029264065","https://openalex.org/W3031504748"],"related_works":["https://openalex.org/W2949846021","https://openalex.org/W2951568450","https://openalex.org/W1731670240","https://openalex.org/W1718449494","https://openalex.org/W2966907487","https://openalex.org/W2140251433","https://openalex.org/W1519727353","https://openalex.org/W2020649503","https://openalex.org/W51126094","https://openalex.org/W2082806671"],"abstract_inverted_index":{"A":[0],"judiciously":[1],"normalized":[2],"database":[3],"schema":[4,39,57,79],"can":[5],"increase":[6],"data":[7,10,14,19],"interpretability,":[8],"reduce":[9],"size,":[11],"and":[12,91,112,126],"improve":[13],"integrity.":[15],"However,":[16],"real":[17],"world":[18],"sets":[20],"are":[21],"often":[22],"stored":[23],"or":[24],"shared":[25],"in":[26],"a":[27,37,41,72,77],"denormalized":[28,42],"state.":[29],"We":[30,75,103],"examine":[31],"the":[32,59,100,133],"problem":[33,51],"of":[34,99],"automatically":[35],"creating":[36],"good":[38],"for":[40,109],"table,":[43],"approaching":[44],"it":[45,116],"as":[46],"an":[47,55,105],"unsupervised":[48],"machine":[49],"learning":[50,107],"which":[52],"must":[53],"learn":[54],"optimal":[56],"from":[58,63],"data.":[60],"This":[61],"differs":[62],"past":[64],"rule-based":[65],"approaches":[66],"that":[67,86,115],"focus":[68],"on":[69,83],"normalization":[70],"into":[71],"canonical":[73],"form.":[74],"define":[76],"principled":[78],"optimization":[80],"criterion,":[81],"based":[82],"Occam's":[84],"razor,":[85],"is":[87,117],"robust":[88],"to":[89,94,119],"noise":[90],"extensible---allowing":[92],"users":[93],"easily":[95],"specify":[96],"desirable":[97],"properties":[98],"resulting":[101],"schema.":[102],"develop":[104],"efficient":[106],"algorithm":[108],"this":[110],"criterion":[111],"empirically":[113],"demonstrate":[114],"3":[118],"100":[120],"times":[121],"faster":[122],"than":[123],"previous":[124],"work":[125],"produces":[127],"higher":[128],"quality":[129],"schemas":[130],"with":[131],"1/5th":[132],"errors.":[134]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}