{"id":"https://openalex.org/W2884499287","doi":"https://doi.org/10.14778/3231751.3231766","title":"Transform-data-by-example (TDE)","display_name":"Transform-data-by-example (TDE)","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2884499287","doi":"https://doi.org/10.14778/3231751.3231766","mag":"2884499287"},"language":"en","primary_location":{"id":"doi:10.14778/3231751.3231766","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3231751.3231766","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/A5034908019","display_name":"Yeye He","orcid":"https://orcid.org/0000-0003-2824-5299"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yeye He","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430971","display_name":"Xu Chu","orcid":"https://orcid.org/0000-0002-0683-8299"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu Chu","raw_affiliation_strings":["Georgia Institute of Technology and Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology and Microsoft Research","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080534589","display_name":"Kris Ganjam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kris Ganjam","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101814491","display_name":"Yudian Zheng","orcid":"https://orcid.org/0000-0001-6537-1521"},"institutions":[{"id":"https://openalex.org/I113979032","display_name":"Twitter (United States)","ror":"https://ror.org/04wt43v05","country_code":"US","type":"company","lineage":["https://openalex.org/I113979032"]},{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Yudian Zheng","raw_affiliation_strings":["Twitter Inc. and Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Twitter Inc. and Microsoft Research","institution_ids":["https://openalex.org/I4210124949","https://openalex.org/I113979032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063257827","display_name":"Vivek Narasayya","orcid":"https://orcid.org/0000-0001-7011-7886"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vivek Narasayya","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038037154","display_name":"Surajit Chaudhuri","orcid":"https://orcid.org/0000-0001-8252-5270"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Surajit Chaudhuri","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.8149,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.97486025,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"11","issue":"10","first_page":"1165","last_page":"1177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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/T11719","display_name":"Data Quality and Management","score":0.9993000030517578,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9984999895095825,"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":0.8032981157302856},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.7328686118125916},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5274779200553894},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.5229578614234924},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5043810606002808},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5031470656394958},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4806174635887146},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46438464522361755},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.46209731698036194},{"id":"https://openalex.org/keywords/business-logic","display_name":"Business logic","score":0.4594714045524597},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4446410834789276},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4178736209869385},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3995109796524048},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3956017792224884},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.359086275100708},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.1255401372909546},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.12168174982070923},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09976598620414734}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8032981157302856},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.7328686118125916},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5274779200553894},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.5229578614234924},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5043810606002808},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5031470656394958},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4806174635887146},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46438464522361755},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.46209731698036194},{"id":"https://openalex.org/C146222976","wikidata":"https://www.wikidata.org/wiki/Q1204997","display_name":"Business logic","level":2,"score":0.4594714045524597},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4446410834789276},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4178736209869385},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3995109796524048},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3956017792224884},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.359086275100708},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.1255401372909546},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.12168174982070923},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09976598620414734},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3231751.3231766","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3231751.3231766","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":[{"display_name":"Industry, innovation and infrastructure","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1502767928","https://openalex.org/W1518364836","https://openalex.org/W1551385575","https://openalex.org/W1592614241","https://openalex.org/W1996505782","https://openalex.org/W2013970953","https://openalex.org/W2067435104","https://openalex.org/W2123845384","https://openalex.org/W2144951274","https://openalex.org/W2146013510","https://openalex.org/W2148738951","https://openalex.org/W2164611950","https://openalex.org/W2182787248","https://openalex.org/W2427822648","https://openalex.org/W2496170334","https://openalex.org/W2574230393","https://openalex.org/W2611988335","https://openalex.org/W2612824201","https://openalex.org/W2616147950","https://openalex.org/W2798323405","https://openalex.org/W2798546256","https://openalex.org/W4233189519","https://openalex.org/W4256244129","https://openalex.org/W6630166281","https://openalex.org/W6686029465"],"related_works":["https://openalex.org/W2378767206","https://openalex.org/W1540871478","https://openalex.org/W328308450","https://openalex.org/W282641168","https://openalex.org/W2376963063","https://openalex.org/W2066396794","https://openalex.org/W2366734808","https://openalex.org/W2003100177","https://openalex.org/W2391444248","https://openalex.org/W2390716080"],"abstract_inverted_index":{"Today,":[0],"business":[1],"analysts":[2],"and":[3,11,22,42,48,76,80,102,136,155,179],"data":[4,14,33,40,121],"scientists":[5],"increasingly":[6],"need":[7,143],"to":[8,45,144,150,162],"clean,":[9],"standardize":[10],"transform":[12],"diverse":[13],"sets,":[15],"such":[16,104],"as":[17],"name,":[18],"address,":[19],"date":[20],"time,":[21],"phone":[23],"number,":[24],"before":[25],"they":[26,99],"can":[27,100,157,182],"perform":[28],"analysis.":[29],"This":[30],"process":[31],"of":[32,39,70,127,173,220,233],"transformation":[34,59,90,106,128,200],"is":[35,43,210,225],"an":[36,171],"important":[37],"part":[38],"preparation,":[41],"known":[44],"be":[46,92],"difficult":[47],"time-consuming":[49],"for":[50,73,96,120,206,222],"end-users.":[51],"Traditionally,":[52],"developers":[53],"have":[54,66],"dealt":[55],"with":[56,167,197],"these":[57],"longstanding":[58],"problems":[60],"using":[61],"custom":[62,71],"code":[63,84],"libraries.":[64],"They":[65],"built":[67],"vast":[68,125],"varieties":[69,126],"logic":[72,129],"name":[74],"parsing":[75],"address":[77],"standardization,":[78],"etc.,":[79],"shared":[81],"their":[82],"source":[83,131],"in":[85,130,239],"places":[86],"like":[87,116],"GitHub.":[88],"Data":[89],"would":[91],"a":[93,117,146,152,195],"lot":[94],"easier":[95],"end-users":[97],"if":[98],"discover":[101],"reuse":[103],"existing":[105,192],"logic.":[107],"We":[108],"developed":[109],"Transform-Data-by-Example":[110],"(":[111],"TDE":[112,123,156,181,202,221,235],"),":[113],"which":[114,209],"works":[115],"search":[118],"engine":[119],"transformations.":[122],"\"indexes\"":[124],"code,":[132],"DLLs,":[133],"web":[134],"services":[135],"mapping":[137],"tables,":[138],"so":[139],"that":[140],"users":[141],"only":[142],"provide":[145],"few":[147],"input/output":[148],"examples":[149],"demonstrate":[151],"desired":[153],"transformation,":[154],"interactively":[158],"find":[159],"relevant":[160],"functions":[161,175],"synthesize":[163],"new":[164],"programs":[165],"consistent":[166],"all":[168],"examples.":[169],"Using":[170],"index":[172],"50K":[174],"crawled":[176],"from":[177],"GitHub":[178],"Stackoverflow,":[180],"already":[183],"handle":[184],"many":[185],"common":[186],"transformations":[187,205],"not":[188],"currently":[189],"supported":[190],"by":[191],"systems.":[193],"On":[194],"benchmark":[196],"over":[198],"200":[199],"tasks,":[201,208],"generates":[203],"correct":[204],"72%":[207],"considerably":[211],"better":[212],"than":[213],"other":[214],"systems":[215],"evaluated.":[216],"A":[217],"beta":[218],"version":[219],"Microsoft":[223,240],"Excel":[224],"available":[226],"via":[227],"Office":[228],"store":[229],"1":[230],".":[231],"Part":[232],"the":[234],"technology":[236],"also":[237],"ships":[238],"Power":[241],"BI.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}