{"id":"https://openalex.org/W4396843693","doi":"https://doi.org/10.1145/3589335.3651441","title":"The Web Data Commons Schema.org Table Corpora","display_name":"The Web Data Commons Schema.org Table Corpora","publication_year":2024,"publication_date":"2024-05-12","ids":{"openalex":"https://openalex.org/W4396843693","doi":"https://doi.org/10.1145/3589335.3651441"},"language":"es","primary_location":{"id":"doi:10.1145/3589335.3651441","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651441","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651441","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651441","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082603069","display_name":"Ralph Peeters","orcid":"https://orcid.org/0000-0003-3174-2616"},"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":"Ralph Peeters","raw_affiliation_strings":["University of Mannheim, Mannheim, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3174-2616","affiliations":[{"raw_affiliation_string":"University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062326789","display_name":"Alexander Brinkmann","orcid":"https://orcid.org/0000-0002-9379-2048"},"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":"Alexander Brinkmann","raw_affiliation_strings":["University of Mannheim, Mannheim, Germany"],"raw_orcid":"https://orcid.org/0000-0002-9379-2048","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"],"raw_orcid":"https://orcid.org/0000-0003-2367-0237","affiliations":[{"raw_affiliation_string":"University of 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":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1079","last_page":"1082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9959999918937683,"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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9959999918937683,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9957000017166138,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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":0.7900424003601074},{"id":"https://openalex.org/keywords/commons","display_name":"Commons","score":0.602033257484436},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5812858939170837},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5170355439186096},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4697834551334381},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.45120418071746826},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27746689319610596},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.08272075653076172}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900424003601074},{"id":"https://openalex.org/C49427245","wikidata":"https://www.wikidata.org/wiki/Q9828451","display_name":"Commons","level":2,"score":0.602033257484436},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5812858939170837},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5170355439186096},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4697834551334381},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.45120418071746826},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27746689319610596},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.08272075653076172},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3589335.3651441","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651441","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651441","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:67187","is_oa":true,"landing_page_url":null,"pdf_url":"https://madoc.bib.uni-mannheim.de/67187/1/3589335.3651441.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":{"id":"doi:10.1145/3589335.3651441","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651441","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651441","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396843693.pdf","grobid_xml":"https://content.openalex.org/works/W4396843693.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2162020046","https://openalex.org/W2196674927","https://openalex.org/W2341748398","https://openalex.org/W2806096072","https://openalex.org/W2889133671","https://openalex.org/W2941366772","https://openalex.org/W2969723769","https://openalex.org/W3008881932","https://openalex.org/W3189373506","https://openalex.org/W4205922070","https://openalex.org/W4232666159","https://openalex.org/W4365456672","https://openalex.org/W4367310562"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4221061324","https://openalex.org/W4293337154","https://openalex.org/W2093076951","https://openalex.org/W3015187458","https://openalex.org/W2029448061","https://openalex.org/W102769829","https://openalex.org/W2166975250","https://openalex.org/W1575237224","https://openalex.org/W1508763253"],"abstract_inverted_index":{"The":[0,107,150],"research":[1,55],"on":[2,167],"table":[3,19,35,64,72,75,119],"representation":[4],"learning,":[5],"data":[6,9,15,157,183],"retrieval,":[7],"and":[8,24,50,82,161,194,244],"integration":[10,155],"in":[11],"the":[12,22,27,31,42,54,60,67,111,133,147,154,176,189,227,230,239,242],"context":[13],"of":[14,26,62,78,105,128,156,170,182,208,229,238,241],"lakes":[16],"requires":[17],"large":[18,34,118],"corpora":[20,36,65,76,112,120],"for":[21,201],"training":[23,163],"evaluation":[25],"developed":[28],"methods.":[29],"Over":[30],"years,":[32],"several":[33],"such":[37],"as":[38,99,101],"WikiTables,":[39],"GitTables,":[40],"or":[41,172],"Dresden":[43],"Web":[44,68],"Table":[45,233],"Corpus":[46],"have":[47,185,195],"been":[48,186,196],"published":[49],"are":[51,218],"used":[52],"by":[53],"community.":[56],"This":[57,224],"paper":[58,225],"complements":[59],"set":[61],"public":[63],"with":[66],"Data":[69],"Commons":[70],"Schema.org":[71,232],"corpora,":[73,243],"two":[74],"consisting":[77],"4.2":[79],"(Release":[80,85],"2020)":[81],"5":[83],"million":[84,180],"2023)":[86],"relational":[87],"tables":[88,124,142,177,200],"describing":[89],"products,":[90],"events,":[91],"local":[92],"businesses,":[93],"job":[94],"postings,":[95],"recipes,":[96],"movies,":[97],"books,":[98],"well":[100],"37":[102],"further":[103],"types":[104,169],"entities.":[106],"feature":[108],"that":[109,122,125,212],"distinguishes":[110],"from":[113,158,188,214],"all":[114,123,141,206],"other":[115],"publicly":[116],"available":[117],"is":[121],"describe":[126,137],"entities":[127,171],"a":[129,144,209,215,221],"specific":[130,168,173,210,216],"type":[131],"use":[132,143,247],"same":[134],"attributes":[135],"to":[136,165],"these":[138],"entities,":[139],"i.e.":[140,205],"shared":[145,151],"schema,":[146],"schema.org":[148],"vocabulary.":[149],"schema":[152],"eases":[153],"different":[159],"sources":[160],"allows":[162],"processes":[164],"focus":[166],"attributes.":[174],"Altogether":[175],"contain":[178],"~653":[179],"rows":[181],"which":[184],"extracted":[187],"Common":[190],"Crawl":[191],"web":[192],"corpus":[193],"grouped":[197],"into":[198,220],"separate":[199],"each":[202],"class/host":[203],"combination,":[204],"records":[207],"class":[211],"originate":[213],"website":[217],"put":[219],"single":[222],"table.":[223],"describes":[226],"creation":[228],"WDC":[231],"Corpora,":[234],"gives":[235],"an":[236],"overview":[237],"content":[240],"discusses":[245],"their":[246],"cases.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
