{"id":"https://openalex.org/W2032655922","doi":"https://doi.org/10.1145/2623330.2623617","title":"Integrating spreadsheet data via accurate and low-effort extraction","display_name":"Integrating spreadsheet data via accurate and low-effort extraction","publication_year":2014,"publication_date":"2014-08-22","ids":{"openalex":"https://openalex.org/W2032655922","doi":"https://doi.org/10.1145/2623330.2623617","mag":"2032655922"},"language":"en","primary_location":{"id":"doi:10.1145/2623330.2623617","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5100457678","display_name":"Zhe Chen","orcid":"https://orcid.org/0000-0002-2919-4481"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Chen","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039133265","display_name":"Michael Cafarella","orcid":"https://orcid.org/0000-0001-6122-0590"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Cafarella","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.9831,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.97349377,"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":"1126","last_page":"1135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/metadata","display_name":"Metadata","score":0.8463402390480042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8457050323486328},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.6699489951133728},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5725449323654175},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5212969779968262},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.5197267532348633},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.4808681607246399},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43351978063583374},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.41321977972984314},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3308405876159668},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20615047216415405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19515782594680786},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1458609700202942}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8463402390480042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8457050323486328},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.6699489951133728},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5725449323654175},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5212969779968262},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5197267532348633},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.4808681607246399},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43351978063583374},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.41321977972984314},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3308405876159668},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20615047216415405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19515782594680786},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1458609700202942},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2623330.2623617","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G3584787450","display_name":null,"funder_award_id":"IIS-1064606","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"},{"id":"https://openalex.org/G6663116342","display_name":null,"funder_award_id":"IIS-1054913","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307783","display_name":"Dow Chemical Company","ror":"https://ror.org/032hx4q18"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W82775311","https://openalex.org/W1511986666","https://openalex.org/W1546474256","https://openalex.org/W1640423250","https://openalex.org/W1732744741","https://openalex.org/W1978492080","https://openalex.org/W1980452149","https://openalex.org/W2006426998","https://openalex.org/W2010598806","https://openalex.org/W2029207367","https://openalex.org/W2048282669","https://openalex.org/W2059216172","https://openalex.org/W2064766209","https://openalex.org/W2066806792","https://openalex.org/W2094728533","https://openalex.org/W2097864578","https://openalex.org/W2098516643","https://openalex.org/W2102189859","https://openalex.org/W2108223890","https://openalex.org/W2116469285","https://openalex.org/W2132667707","https://openalex.org/W2138187595","https://openalex.org/W2140116426","https://openalex.org/W2147026797","https://openalex.org/W2147880316","https://openalex.org/W2164918853","https://openalex.org/W2166376630","https://openalex.org/W6603353687","https://openalex.org/W6636567206"],"related_works":["https://openalex.org/W3082848404","https://openalex.org/W1979583797","https://openalex.org/W2109986081","https://openalex.org/W2016864125","https://openalex.org/W2417308975","https://openalex.org/W2372254676","https://openalex.org/W4297589944","https://openalex.org/W4368755698","https://openalex.org/W2964129930","https://openalex.org/W2793679056"],"abstract_inverted_index":{"Spreadsheets":[0],"contain":[1],"valuable":[2],"data":[3,15,19,26,78],"on":[4,49,137],"many":[5,108],"topics.":[6],"However,":[7],"spreadsheets":[8,92],"are":[9],"difficult":[10],"to":[11,20,28,74,104],"integrate":[12],"with":[13,123],"other":[14],"sources.":[16],"Converting":[17],"spreadsheet":[18,58,77,96],"the":[21,62,76,84,120,127],"relational":[22,30,42],"model":[23],"would":[24],"allow":[25],"analysts":[27],"use":[29],"integration":[31,59],"tools.":[32],"We":[33],"propose":[34],"a":[35,99,116,132],"two-phase":[36],"semiautomatic":[37],"system":[38,55],"that":[39,115],"extracts":[40],"accurate":[41,121],"metadata":[43,73],"while":[44],"minimizing":[45],"user":[46],"effort.":[47],"Based":[48],"an":[50],"undirected":[51],"graphical":[52,69],"model,":[53],"our":[54],"enables":[56],"downstream":[57],"applications.":[60],"First,":[61],"automatic":[63],"extractor":[64],"uses":[65],"hints":[66],"from":[67],"spreadsheets'":[68],"style":[70],"and":[71],"recovered":[72],"extract":[75],"as":[79,81],"accurately":[80],"possible.":[82],"Second,":[83],"interactive":[85],"repair":[86,103],"identifies":[87],"similar":[88],"regions":[89],"in":[90],"distinct":[91],"scattered":[93],"across":[94],"large":[95],"corpora,":[97],"allowing":[98],"user's":[100],"single":[101],"manual":[102,128],"be":[105],"amortized":[106],"over":[107],"possible":[109],"extraction":[110,122],"errors.":[111],"Our":[112],"experiments":[113],"show":[114],"human":[117],"can":[118],"obtain":[119],"just":[124],"31%":[125],"of":[126],"operations":[129],"required":[130],"by":[131],"standard":[133],"classification":[134],"based":[135],"technique":[136],"two":[138],"real-world":[139],"datasets.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}