{"id":"https://openalex.org/W3094005171","doi":"https://doi.org/10.1145/3340531.3412027","title":"Extracting N-ary Facts from Wikipedia Table Clusters","display_name":"Extracting N-ary Facts from Wikipedia Table Clusters","publication_year":2020,"publication_date":"2020-10-19","ids":{"openalex":"https://openalex.org/W3094005171","doi":"https://doi.org/10.1145/3340531.3412027","mag":"3094005171"},"language":"en","primary_location":{"id":"doi:10.1145/3340531.3412027","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ir.cwi.nl/pub/30002/30002.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033110170","display_name":"Benno Kruit","orcid":null},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Benno Kruit","raw_affiliation_strings":["Centrum Wiskunde & Informatica, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Centrum Wiskunde & Informatica, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058712681","display_name":"Peter Boncz","orcid":"https://orcid.org/0000-0001-6256-0140"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Peter Boncz","raw_affiliation_strings":["Centrum Wiskunde & Informatica, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Centrum Wiskunde & Informatica, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090620447","display_name":"Jacopo Urbani","orcid":"https://orcid.org/0000-0002-0717-3559"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jacopo Urbani","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033110170"],"corresponding_institution_ids":["https://openalex.org/I1341640284"],"apc_list":null,"apc_paid":null,"fwci":0.5487,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74223303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"655","last_page":"664"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.994700014591217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7952587008476257},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.7947732210159302},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.539585530757904},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5265080332756042},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5221726894378662},{"id":"https://openalex.org/keywords/decision-table","display_name":"Decision table","score":0.47794225811958313},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4071013629436493},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3827061057090759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26435205340385437},{"id":"https://openalex.org/keywords/rough-set","display_name":"Rough set","score":0.24145200848579407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7952587008476257},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7947732210159302},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.539585530757904},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5265080332756042},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5221726894378662},{"id":"https://openalex.org/C172967692","wikidata":"https://www.wikidata.org/wiki/Q747762","display_name":"Decision table","level":3,"score":0.47794225811958313},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4071013629436493},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3827061057090759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26435205340385437},{"id":"https://openalex.org/C111012933","wikidata":"https://www.wikidata.org/wiki/Q3137210","display_name":"Rough set","level":2,"score":0.24145200848579407}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3340531.3412027","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:cwi.nl:30002","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/30002","pdf_url":"https://ir.cwi.nl/pub/30002/30002.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:research.vu.nl:publications/18d1835b-b862-4a4d-8005-a652d9004c8c","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/citedby.url?scp=85095865121&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306400546","display_name":"Digital Academic REpository of VU University Amsterdam (Vrije Universiteit Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kruit, B, Boncz, P & Urbani, J 2020, Extracting N-ary Facts from Wikipedia Table Clusters. in CIKM '20 : Proceedings of the 29th ACM International Conference on Information & Knowledge Management. International Conference on Information and Knowledge Management, Proceedings, Association for Computing Machinery, pp. 655-664, 29th ACM International Conference on Information and Knowledge Management, CIKM 2020, Virtual, Online, Ireland, 19/10/20. https://doi.org/10.1145/3340531.3412027","raw_type":"contributionToPeriodical"},{"id":"pmh:vu:oai:research.vu.nl:publications/18d1835b-b862-4a4d-8005-a652d9004c8c","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/18d1835b-b862-4a4d-8005-a652d9004c8c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CIKM '20: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, 655 - 664","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"pmh:oai:cwi.nl:30002","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/30002","pdf_url":"https://ir.cwi.nl/pub/30002/30002.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3094005171.pdf","grobid_xml":"https://content.openalex.org/works/W3094005171.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W102383941","https://openalex.org/W1552847225","https://openalex.org/W1908991493","https://openalex.org/W1969621019","https://openalex.org/W1995996823","https://openalex.org/W1996505782","https://openalex.org/W2016465393","https://openalex.org/W2020022499","https://openalex.org/W2022708471","https://openalex.org/W2070491211","https://openalex.org/W2080133951","https://openalex.org/W2131681506","https://openalex.org/W2140116426","https://openalex.org/W2157060173","https://openalex.org/W2162020046","https://openalex.org/W2162833336","https://openalex.org/W2325923789","https://openalex.org/W2340354588","https://openalex.org/W2400256190","https://openalex.org/W2425367731","https://openalex.org/W2529049456","https://openalex.org/W2593864460","https://openalex.org/W2613995098","https://openalex.org/W2798664493","https://openalex.org/W2945114697","https://openalex.org/W2952402694","https://openalex.org/W2980791946","https://openalex.org/W3099768174","https://openalex.org/W4213009331","https://openalex.org/W4235169531","https://openalex.org/W6766223035"],"related_works":["https://openalex.org/W2047835521","https://openalex.org/W4394360958","https://openalex.org/W64552174","https://openalex.org/W2361933495","https://openalex.org/W2360959806","https://openalex.org/W2025955965","https://openalex.org/W1964637661","https://openalex.org/W4286964398","https://openalex.org/W3201074950","https://openalex.org/W2033543900"],"abstract_inverted_index":{"Tables":[0],"in":[1,20],"Wikipedia":[2,152],"articles":[3],"contain":[4,35,73],"a":[5,21,80,132],"wealth":[6],"of":[7,32,39,105,169],"knowledge":[8,82,119],"that":[9,30,53,85,118,134,155],"would":[10],"be":[11],"useful":[12],"for":[13],"many":[14,31,160,170],"applications":[15],"if":[16],"it":[17],"were":[18],"structured":[19],"more":[22,74],"coherent,":[23],"queryable":[24],"form.":[25],"An":[26],"important":[27],"problem":[28,104],"is":[29],"such":[33],"tables":[34,49,67,96,111,153],"the":[36,103,109,115,125,142,167],"same":[37],"type":[38],"knowledge,":[40],"but":[41],"have":[42],"different":[43],"layouts":[44],"and/or":[45],"schemata.":[46],"Moreover,":[47],"some":[48,66],"refer":[50],"to":[51,57,101,114,124,139,166],"entities":[52,122],"we":[54],"can":[55,158],"link":[56],"Knowledge":[58],"Bases":[59],"(KBs),":[60],"while":[61,71],"others":[62,72],"do":[63],"not.":[64],"Finally,":[65,128],"express":[68],"entity-attribute":[69],"relations,":[70],"complex":[75],"n-ary":[76,146,172],"relations.":[77,147,173],"We":[78],"propose":[79],"novel":[81,171],"extraction":[83,168],"technique":[84,133],"tackles":[86],"these":[87],"problems.":[88],"Our":[89,148],"method":[90,130],"first":[91],"transforms":[92],"and":[93,144],"clusters":[94],"similar":[95,162],"into":[97],"fewer":[98],"unified":[99,110],"ones":[100],"overcome":[102],"table":[106,143],"diversity.":[107],"Then,":[108],"are":[112],"linked":[113],"KB":[116],"so":[117],"about":[120],"popular":[121],"propagates":[123],"unpopular":[126],"ones.":[127],"our":[129,156],"applies":[131],"relies":[135],"on":[136],"functional":[137],"dependencies":[138],"judiciously":[140],"interpret":[141],"extract":[145],"experiments":[149],"over":[150],"1.5M":[151],"show":[154],"clustering":[157],"group":[159],"semantically":[161],"tables.":[163],"This":[164],"leads":[165]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}