{"id":"https://openalex.org/W2035274534","doi":"https://doi.org/10.1109/icde.2014.6816716","title":"A hybrid machine-crowdsourcing system for matching web tables","display_name":"A hybrid machine-crowdsourcing system for matching web tables","publication_year":2014,"publication_date":"2014-03-01","ids":{"openalex":"https://openalex.org/W2035274534","doi":"https://doi.org/10.1109/icde.2014.6816716","mag":"2035274534"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2014.6816716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2014.6816716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 30th International Conference on Data Engineering","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/A5100739546","display_name":"Ju Fan","orcid":"https://orcid.org/0000-0003-4729-9903"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Ju Fan","raw_affiliation_strings":["National University of Singapore","Nat. Univ. of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109054289","display_name":"Meiyu Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Meiyu Lu","raw_affiliation_strings":["National University of Singapore","Nat. Univ. of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024892041","display_name":"Beng Chin Ooi","orcid":"https://orcid.org/0000-0003-4446-1100"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Beng Chin Ooi","raw_affiliation_strings":["National University of Singapore","Nat. Univ. of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026007789","display_name":"Wang-Chiew Tan","orcid":"https://orcid.org/0009-0003-4659-2291"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang-Chiew Tan","raw_affiliation_strings":["University of California","University of California USA"],"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]},{"raw_affiliation_string":"University of California USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032263010","display_name":"Meihui Zhang","orcid":"https://orcid.org/0000-0002-0752-9877"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Meihui Zhang","raw_affiliation_strings":["National University of Singapore","Nat. Univ. of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100739546"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":17.65774067,"has_fulltext":false,"cited_by_count":105,"citation_normalized_percentile":{"value":0.99498255,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"976","last_page":"987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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/T12016","display_name":"Web Data Mining and Analysis","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"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/schema-matching","display_name":"Schema matching","score":0.9007538557052612},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.8914744853973389},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7814751267433167},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.5942696332931519},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.553482174873352},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5485504269599915},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5271273255348206},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49700573086738586},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.4961577355861664},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3907471299171448},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.30390167236328125},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.18854671716690063},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09223133325576782}],"concepts":[{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.9007538557052612},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.8914744853973389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7814751267433167},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.5942696332931519},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.553482174873352},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5485504269599915},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5271273255348206},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49700573086738586},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.4961577355861664},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3907471299171448},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.30390167236328125},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.18854671716690063},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09223133325576782},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2014.6816716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2014.6816716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 30th International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.649.6638","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.649.6638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/~ooibc/icde14-webtable.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1680189815","https://openalex.org/W1969621019","https://openalex.org/W1996505782","https://openalex.org/W2008896880","https://openalex.org/W2022166150","https://openalex.org/W2035274534","https://openalex.org/W2053653724","https://openalex.org/W2056748234","https://openalex.org/W2066806792","https://openalex.org/W2069897123","https://openalex.org/W2076357412","https://openalex.org/W2085999189","https://openalex.org/W2092364718","https://openalex.org/W2094728533","https://openalex.org/W2101168711","https://openalex.org/W2108223890","https://openalex.org/W2108991785","https://openalex.org/W2111869785","https://openalex.org/W2135767707","https://openalex.org/W2140116426","https://openalex.org/W2145007893","https://openalex.org/W2170188121","https://openalex.org/W2288244345","https://openalex.org/W2406114359","https://openalex.org/W3146259567","https://openalex.org/W4240555197","https://openalex.org/W6674993841","https://openalex.org/W6685116542","https://openalex.org/W6696516842","https://openalex.org/W6713576725"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W113172935","https://openalex.org/W3208717180","https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W2014400548","https://openalex.org/W4301779090","https://openalex.org/W2029826694","https://openalex.org/W4298139853","https://openalex.org/W1990272589"],"abstract_inverted_index":{"Abstract\u2014The":[0],"Web":[1],"is":[2,36,48],"teeming":[3],"with":[4,17],"rich":[5],"structured":[6],"infor-mation":[7],"in":[8,74,113,146],"the":[9,18,54,72,92,110,124,139,147,163,173,181,189,197,201,204,208],"form":[10],"of":[11,32,105,129,203,210],"HTML":[12],"tables,":[13],"which":[14],"provides":[15],"us":[16],"opportunity":[19],"to":[20,37,52,71,109,144,161,180,192],"build":[21],"a":[22,49,82,98,106,114,153,184,239],"knowledge":[23,116],"repository":[24],"by":[25],"integrating":[26],"these":[27],"tables.":[28,76],"An":[29],"essential":[30],"problem":[31,125],"web":[33,42,67,75,86,107,131,221],"data":[34,223],"integration":[35],"discover":[38],"semantic":[39],"correspondences":[40],"between":[41],"table":[43,68,87,108,132,222],"columns,":[44],"and":[45,187],"schema":[46,59,234],"matching":[47,60,69,88,178,235],"popular":[50],"means":[51],"determine":[53],"se-mantic":[55],"correspondences.":[56],"However,":[57],"conventional":[58],"techniques":[61,236],"are":[62,141],"not":[63],"always":[64],"effective":[65],"for":[66,85,165,200,242],"due":[70,143],"incompleteness":[73,145],"In":[77],"this":[78],"paper,":[79],"we":[80,96,151],"propose":[81,97],"two-pronged":[83,230],"approach":[84,100,122,231],"that":[89,101,118,126,157,228],"effectively":[90],"addresses":[91],"above":[93],"difficulties.":[94],"First,":[95],"concept-based":[99],"maps":[102],"each":[103],"column":[104,148],"best":[111,198],"concept,":[112],"well-developed":[115],"base,":[117],"represents":[119],"it.":[120],"This":[121],"overcomes":[123],"sometimes":[127],"values":[128],"two":[130,219],"columns":[133,140],"may":[134],"be":[135],"disjoint,":[136],"even":[137],"though":[138],"related,":[142],"values.":[149],"Second,":[150],"develop":[152],"hybrid":[154],"machine-crowdsourcing":[155],"framework":[156,171,212],"leverages":[158],"human":[159],"intelligence":[160],"discern":[162],"concepts":[164],"\u201cdifficult":[166],"\u201d":[167,176],"columns.":[168,205],"Our":[169],"overall":[170],"assigns":[172],"most":[174],"\u201cbeneficial":[175],"column-to-concept":[177],"tasks":[179],"crowd":[182],"under":[183],"given":[185],"budget":[186],"utilizes":[188],"crowdsourcing":[190],"result":[191],"help":[193],"our":[194,211,229],"algorithm":[195],"infer":[196],"matches":[199],"rest":[202],"We":[206],"validate":[207],"effectiveness":[209],"through":[213],"an":[214],"extensive":[215],"experimental":[216],"study":[217],"over":[218],"real-world":[220],"sets.":[224],"The":[225],"results":[226],"show":[227],"outperforms":[232],"existing":[233],"at":[237],"only":[238],"low":[240],"cost":[241],"crowdsourcing.":[243],"I.":[244]},"counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}