{"id":"https://openalex.org/W2293101314","doi":"https://doi.org/10.1145/2837614.2837668","title":"Transforming spreadsheet data types using examples","display_name":"Transforming spreadsheet data types using examples","publication_year":2016,"publication_date":"2016-01-07","ids":{"openalex":"https://openalex.org/W2293101314","doi":"https://doi.org/10.1145/2837614.2837668","mag":"2293101314"},"language":"en","primary_location":{"id":"doi:10.1145/2837614.2837668","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2837614.2837668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd Annual ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages","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/A5045091456","display_name":"Rishabh Singh","orcid":"https://orcid.org/0000-0003-1714-9656"},"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rishabh Singh","raw_affiliation_strings":["Microsoft Research, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011543162","display_name":"Sumit Gulwani","orcid":"https://orcid.org/0000-0002-9226-9634"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sumit Gulwani","raw_affiliation_strings":["Microsoft Research, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045091456"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":9.7453,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.98216259,"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":"343","last_page":"356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9987999796867371,"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":0.9987999796867371,"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/T13197","display_name":"Spreadsheets and End-User Computing","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8496215343475342},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.6080518960952759},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6047258377075195},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5471999049186707},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5177037715911865},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5008130073547363},{"id":"https://openalex.org/keywords/domain-specific-language","display_name":"Domain-specific language","score":0.4434702694416046},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.43076810240745544},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4250001311302185},{"id":"https://openalex.org/keywords/language-construct","display_name":"Language construct","score":0.41114112734794617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3524287939071655},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34004226326942444},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.31596410274505615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8496215343475342},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.6080518960952759},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6047258377075195},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5471999049186707},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5177037715911865},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5008130073547363},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.4434702694416046},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.43076810240745544},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4250001311302185},{"id":"https://openalex.org/C48859967","wikidata":"https://www.wikidata.org/wiki/Q6486712","display_name":"Language construct","level":2,"score":0.41114112734794617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3524287939071655},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34004226326942444},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31596410274505615},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2837614.2837668","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2837614.2837668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd Annual ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1792831685","https://openalex.org/W1890754682","https://openalex.org/W1982280055","https://openalex.org/W1990751139","https://openalex.org/W1997199152","https://openalex.org/W1999298208","https://openalex.org/W2009802401","https://openalex.org/W2012312630","https://openalex.org/W2015914309","https://openalex.org/W2018365488","https://openalex.org/W2046536636","https://openalex.org/W2048027175","https://openalex.org/W2049311030","https://openalex.org/W2057156093","https://openalex.org/W2061503494","https://openalex.org/W2072764742","https://openalex.org/W2096679454","https://openalex.org/W2105315191","https://openalex.org/W2106895292","https://openalex.org/W2110848488","https://openalex.org/W2121932026","https://openalex.org/W2122735631","https://openalex.org/W2126650630","https://openalex.org/W2132525863","https://openalex.org/W2134579392","https://openalex.org/W2137824953","https://openalex.org/W2142126234","https://openalex.org/W2146105230","https://openalex.org/W2160985005","https://openalex.org/W2162091689","https://openalex.org/W2163671349","https://openalex.org/W2187606973","https://openalex.org/W2276356546","https://openalex.org/W2399923814","https://openalex.org/W2406252837","https://openalex.org/W2626106541","https://openalex.org/W4214807841","https://openalex.org/W4237412827","https://openalex.org/W4245234767","https://openalex.org/W4246839229"],"related_works":["https://openalex.org/W2993859764","https://openalex.org/W4243817981","https://openalex.org/W2133708976","https://openalex.org/W2500725017","https://openalex.org/W1995048285","https://openalex.org/W2169355987","https://openalex.org/W2483415553","https://openalex.org/W4235797919","https://openalex.org/W1966356977","https://openalex.org/W2293614426"],"abstract_inverted_index":{"Cleaning":[0],"spreadsheet":[1,12],"data":[2,32,51,58,63,110,136,156],"types":[3,15,33,111],"is":[4,64,132,142],"a":[5,103,118,124,179,191],"common":[6],"problem":[7,83],"faced":[8],"by":[9,105],"millions":[10],"of":[11,108,155,193],"users.":[13],"Data":[14],"such":[16,50],"as":[17,201],"date,":[18],"time,":[19],"name,":[20],"and":[21,27,36,60,68,72,78,159,173,205,219],"units":[22],"are":[23,86,94],"ubiquitous":[24],"in":[25,187],"spreadsheets,":[26],"cleaning":[28,49,109],"transformations":[29],"on":[30,144,210],"these":[31],"involve":[34],"parsing":[35],"pretty":[37],"printing":[38],"their":[39,96],"string":[40],"representations.":[41],"This":[42,163],"presents":[43],"many":[44],"challenges":[45],"to":[46,169],"users":[47],"because":[48],"requires":[52],"some":[53,76],"background":[54],"knowledge":[55],"about":[56],"the":[57,90,114,167,184],"itself":[59],"moreover":[61],"this":[62,82,99,188],"typically":[65],"non-uniform,":[66,171],"unstructured,":[67,172],"ambiguous.":[69],"Spreadsheet":[70],"systems":[71],"Programming":[73],"Languages":[74],"provide":[75],"UI-based":[77],"programmatic":[79],"solutions":[80],"for":[81,89],"but":[84],"they":[85],"either":[87],"insufficient":[88],"user's":[91],"needs":[92],"or":[93],"beyond":[95],"expertise.":[97],"In":[98],"paper,":[100],"we":[101],"present":[102,178,206],"programming":[104],"example":[106],"methodology":[107],"that":[112,131,182],"learns":[113,183],"desired":[115,185],"transformation":[116],"from":[117,190,215],"few":[119],"input-output":[120,194],"examples.":[121,195],"We":[122,176,196],"propose":[123],"domain":[125],"specific":[126],"language":[127,168,189],"with":[128,134],"probabilistic":[129,140,164],"semantics":[130,141,165],"parameterized":[133],"declarative":[135],"type":[137,157],"definitions.":[138],"The":[139],"based":[143],"three":[145],"key":[146],"aspects:":[147],"(i)":[148],"approximate":[149],"predicate":[150],"matching,":[151],"(ii)":[152],"joint":[153],"learning":[154],"interpretation,":[158],"(iii)":[160],"weighted":[161],"branches.":[162],"enables":[166],"handle":[170],"ambiguous":[174],"data.":[175],"then":[177],"synthesis":[180],"algorithm":[181,200],"program":[186],"set":[192],"have":[197],"implemented":[198],"our":[199],"an":[202],"Excel":[203,220],"add-in":[204],"its":[207],"successful":[208],"evaluation":[209],"55":[211],"benchmark":[212],"problems":[213],"obtained":[214],"online":[216],"help":[217],"forums":[218],"product":[221],"team.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":6}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}