{"id":"https://openalex.org/W2752618741","doi":"https://doi.org/10.14778/3137628.3137657","title":"Stitching web tables for improving matching quality","display_name":"Stitching web tables for improving matching quality","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2752618741","doi":"https://doi.org/10.14778/3137628.3137657","mag":"2752618741"},"language":"en","primary_location":{"id":"doi:10.14778/3137628.3137657","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3137628.3137657","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/A5017822280","display_name":"Oliver Lehmberg","orcid":null},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oliver Lehmberg","raw_affiliation_strings":["Universit\u00e4t Mannheim, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076876024","display_name":"Christian Bizer","orcid":"https://orcid.org/0000-0003-2367-0237"},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Bizer","raw_affiliation_strings":["Universit\u00e4t Mannheim, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177802217"],"apc_list":null,"apc_paid":null,"fwci":6.2256,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.96501487,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"10","issue":"11","first_page":"1502","last_page":"1513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9977999925613403,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8057010173797607},{"id":"https://openalex.org/keywords/image-stitching","display_name":"Image stitching","score":0.6628358960151672},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5668661594390869},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5519086718559265},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.5206124782562256},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5102276802062988},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4646190404891968},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.4361494183540344},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.33166176080703735},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2953924536705017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20791524648666382},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10553956031799316},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09682139754295349},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.07950377464294434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057010173797607},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.6628358960151672},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5668661594390869},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5519086718559265},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.5206124782562256},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5102276802062988},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4646190404891968},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.4361494183540344},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33166176080703735},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2953924536705017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20791524648666382},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10553956031799316},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09682139754295349},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.07950377464294434}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3137628.3137657","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3137628.3137657","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"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:42790","is_oa":false,"landing_page_url":"http://ub-madoc.bib.uni-mannheim.de/42790/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196315","display_name":"MADOC (University of Mannheim)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177802217","host_organization_name":"University of Mannheim","host_organization_lineage":["https://openalex.org/I177802217"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Zeitschriftenartikel"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W92812941","https://openalex.org/W1495062271","https://openalex.org/W1534024124","https://openalex.org/W1552847225","https://openalex.org/W1721994796","https://openalex.org/W1875032969","https://openalex.org/W1969092646","https://openalex.org/W1969621019","https://openalex.org/W1989215876","https://openalex.org/W1996505782","https://openalex.org/W1998982581","https://openalex.org/W2008896880","https://openalex.org/W2016048023","https://openalex.org/W2016753842","https://openalex.org/W2020022499","https://openalex.org/W2027780984","https://openalex.org/W2092364718","https://openalex.org/W2108223890","https://openalex.org/W2108489852","https://openalex.org/W2111869785","https://openalex.org/W2122604280","https://openalex.org/W2140116426","https://openalex.org/W2157060173","https://openalex.org/W2338381085","https://openalex.org/W2340354588","https://openalex.org/W2341748398","https://openalex.org/W2398606196","https://openalex.org/W2400256190","https://openalex.org/W2402694377","https://openalex.org/W2403920869","https://openalex.org/W2406114359","https://openalex.org/W2425367731","https://openalex.org/W2439326083","https://openalex.org/W2529049456","https://openalex.org/W2604190938","https://openalex.org/W6712839960","https://openalex.org/W6713196223","https://openalex.org/W6713576725"],"related_works":["https://openalex.org/W2767781638","https://openalex.org/W3004796044","https://openalex.org/W2359068514","https://openalex.org/W2357241418","https://openalex.org/W2373668538","https://openalex.org/W2056254149","https://openalex.org/W2086064646","https://openalex.org/W2119135658","https://openalex.org/W2364554164","https://openalex.org/W2385034530"],"abstract_inverted_index":{"HTML":[0],"tables":[1,16,43,81,130,159,172,184,215,229,266,274,283],"on":[2],"web":[3,15,58,80,93,111,129,175,214,219,282],"pages":[4],"(\"web":[5],"tables\")":[6],"cover":[7],"a":[8,110,120,126,164],"wide":[9],"variety":[10],"of":[11,57,69,79,99,128,155,273],"topics.":[12],"Data":[13],"from":[14,173,216,278],"can":[17,36],"thus":[18],"be":[19,37,45],"useful":[20],"for":[21,39,153,255,261],"tasks":[22],"such":[23],"as":[24,285,287],"knowledge":[25,50,114,187],"base":[26,51,53,115,188,190],"completion":[27],"or":[28,52,189],"ad":[29],"hoc":[30],"table":[31,34,59,94,112,191,239],"extension.":[32],"Before":[33],"data":[35],"used":[38,90],"these":[40,182],"tasks,":[41],"the":[42,48,62,66,70,77,85,136,156,161,171,186,210,217,222,243,248,265,271],"must":[44],"matched":[46],"to":[47,91,113,149,168,185,213,227,269,284],"respective":[49],"table.":[54],"The":[55],"challenges":[56],"matching":[60,95,116,123,201,245,249],"are":[61,82,89],"high":[63,232],"heterogeneity":[64,223],"and":[65,118,180,224,258],"small":[67,158],"size":[68],"tables.":[71,101,290],"Though":[72],"it":[73],"is":[74,132],"known":[75],"that":[76,88,131,139,145,237],"majority":[78],"very":[83,157,231],"small,":[84],"gold":[86,137],"standards":[87,138],"compare":[92],"systems":[96,147],"mostly":[97],"consist":[98],"larger":[100,178],"In":[102],"this":[103,194],"experimental":[104],"paper,":[105],"we":[106,166,197],"evaluate":[107,198],"T2K":[108,256],"Match,":[109],"system,":[117],"COMA,":[119],"standard":[121],"schema":[122,200],"tool,":[124],"using":[125],"sample":[127],"more":[133],"realistic":[134],"than":[135],"were":[140],"previously":[141],"used.":[142],"We":[143],"find":[144],"both":[146],"fail":[148],"produce":[150],"correct":[151],"results":[152,250],"many":[154],"in":[160,203,253,275],"sample.":[162],"As":[163],"remedy,":[165],"propose":[167],"stitch":[169,228],"(combine)":[170],"each":[174],"site":[176,220],"into":[177],"ones":[179],"match":[181],"enlarged":[183],"afterwards.":[192],"For":[193],"stitching":[195,211,240,264],"process,":[196],"different":[199],"methods":[202],"combination":[204],"with":[205,230],"holistic":[206],"correspondence":[207],"refinement.":[208],"Limiting":[209],"procedure":[212],"same":[218],"decreases":[221],"allows":[225,267],"us":[226,268],"precision.":[233],"Our":[234],"experiments":[235],"show":[236],"applying":[238],"before":[241],"running":[242],"actual":[244],"method":[246],"improves":[247],"by":[251,259],"0.38":[252],"F1-measure":[254],"Match":[257],"0.14":[260],"COMA.":[262],"Also,":[263],"reduce":[270],"amount":[272],"our":[276],"corpus":[277],"5":[279],"million":[280],"original":[281],"few":[286],"100,000":[288],"stitched":[289]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}