{"id":"https://openalex.org/W2945114697","doi":"https://doi.org/10.1145/3323878.3325806","title":"Profiling the semantics of n-ary web table data","display_name":"Profiling the semantics of n-ary web table data","publication_year":2019,"publication_date":"2019-05-21","ids":{"openalex":"https://openalex.org/W2945114697","doi":"https://doi.org/10.1145/3323878.3325806","mag":"2945114697"},"language":"en","primary_location":{"id":"doi:10.1145/3323878.3325806","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3323878.3325806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Semantic Big Data","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/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":true,"raw_author_name":"Oliver Lehmberg","raw_affiliation_strings":["University of Mannheim, Mannheim, Germany"],"affiliations":[{"raw_affiliation_string":"University of 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":["University of Mannheim, Mannheim, Germany"],"affiliations":[{"raw_affiliation_string":"University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017822280"],"corresponding_institution_ids":["https://openalex.org/I177802217"],"apc_list":null,"apc_paid":null,"fwci":0.1981,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56039441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2012","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9929999709129333,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7938137650489807},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6488099694252014},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6314198970794678},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6078116297721863},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5138295292854309},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4494308829307556},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.41822999715805054},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.284298837184906},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08171415328979492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7938137650489807},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6488099694252014},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6314198970794678},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6078116297721863},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5138295292854309},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4494308829307556},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41822999715805054},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.284298837184906},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08171415328979492}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3323878.3325806","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3323878.3325806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Semantic Big Data","raw_type":"proceedings-article"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:50822","is_oa":false,"landing_page_url":"https://madoc.bib.uni-mannheim.de/50822/","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":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1495062271","https://openalex.org/W1721994796","https://openalex.org/W1751871005","https://openalex.org/W1881756506","https://openalex.org/W1996505782","https://openalex.org/W2016048023","https://openalex.org/W2016753842","https://openalex.org/W2020022499","https://openalex.org/W2092364718","https://openalex.org/W2108223890","https://openalex.org/W2111869785","https://openalex.org/W2122604280","https://openalex.org/W2138556038","https://openalex.org/W2140116426","https://openalex.org/W2166549982","https://openalex.org/W2251758222","https://openalex.org/W2290320465","https://openalex.org/W2340354588","https://openalex.org/W2341748398","https://openalex.org/W2400256190","https://openalex.org/W2403920869","https://openalex.org/W2434080373","https://openalex.org/W2517489125","https://openalex.org/W2526076264","https://openalex.org/W2529049456","https://openalex.org/W2588322767","https://openalex.org/W2604190938","https://openalex.org/W2604250586","https://openalex.org/W2752618741","https://openalex.org/W2946370960"],"related_works":["https://openalex.org/W4394360958","https://openalex.org/W2161444195","https://openalex.org/W2589019771","https://openalex.org/W2948670949","https://openalex.org/W4288047943","https://openalex.org/W2985540061","https://openalex.org/W2185012154","https://openalex.org/W4252521128","https://openalex.org/W2535940710","https://openalex.org/W2000745862"],"abstract_inverted_index":{"The":[0,195],"Web":[1,275],"contains":[2],"millions":[3],"of":[4,12,21,28,67,112,122,135,167,175,197,205,221,227,237,248,282],"relational":[5],"HTML":[6,91],"tables,":[7],"which":[8],"cover":[9],"a":[10,25,77,109,133],"multitude":[11],"different,":[13],"often":[14],"very":[15],"specific":[16,290],"topics.":[17],"This":[18],"rich":[19],"pool":[20],"data":[22,36,65,126,276],"has":[23],"motivated":[24],"growing":[26],"body":[27],"research":[29],"on":[30,76,97,254,261],"methods":[31],"that":[32,62,71,82,103,201,232,285],"use":[33,235],"web":[34,63,124,138,145,152,223],"table":[35,64,125,153,182],"to":[37,48,117,149,162,186,279,288],"extend":[38],"local":[39],"tables":[40,96,139],"with":[41,147],"additional":[42],"attributes":[43,154],"or":[44,184,218],"add":[45],"missing":[46],"facts":[47],"knowledge":[49],"bases.":[50],"Nearly":[51],"all":[52],"existing":[53],"approaches":[54],"for":[55,108,127,240,273],"these":[56,176,211,267],"tasks":[57],"build":[58],"upon":[59],"the":[60,83,90,98,113,120,165,168,173,181,190,193,198,206,216,219,222,228,241,271,280,283],"assumption":[61],"consists":[66],"binary":[68],"relations,":[69],"meaning":[70],"an":[72],"attribute":[73,85],"value":[74,86],"depends":[75],"single":[78],"key":[79,84],"attribute,":[80,244],"and":[81,171,263],"is":[87],"contained":[88],"in":[89,180,225],"table.":[92,194],"Inspecting":[93],"randomly":[94],"chosen":[95],"Web,":[99],"however,":[100],"quickly":[101],"reveals":[102],"both":[104],"assumptions":[105],"are":[106,155,160,178,208,286],"wrong":[107],"large":[110],"fraction":[111],"tables.":[114],"In":[115],"order":[116],"better":[118],"understand":[119],"potential":[121],"non-binary":[123,169],"downstream":[128],"applications,":[129],"this":[130],"papers":[131],"analyses":[132],"corpus":[134,199],"5":[136],"million":[137],"originating":[140],"from":[141,189,215],"80":[142],"thousand":[143],"different":[144,233],"sites":[146],"respect":[148],"how":[150],"many":[151],"non-binary,":[156],"what":[157],"composite":[158],"keys":[159,177,236,284],"required":[161],"correctly":[163],"interpret":[164],"semantics":[166],"attributes,":[170],"whether":[172],"values":[174],"found":[179],"itself":[183],"need":[185],"be":[187],"extracted":[188],"page":[191,224],"surrounding":[192],"profiling":[196],"shows":[200],"at":[202],"least":[203],"38%":[204],"relations":[207,212],"non-binary.":[209],"Recognizing":[210],"requires":[213],"information":[214],"title":[217],"URL":[220],"50%":[226],"cases.":[229],"We":[230],"find":[231],"websites":[234,249],"varying":[238],"length":[239],"same":[242],"dependent":[243],"e.g.":[245],"one":[246],"cluster":[247,257],"presents":[250,258],"employment":[251],"numbers":[252],"depending":[253,260],"time,":[255],"another":[256],"them":[259],"time":[262],"profession.":[264],"By":[265],"identifying":[266],"clusters,":[268],"we":[269],"lay":[270],"foundation":[272],"selecting":[274],"sources":[277],"according":[278],"specificity":[281],"used":[287],"determine":[289],"attributes.":[291]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}