{"id":"https://openalex.org/W2006149654","doi":"https://doi.org/10.1145/1519103.1519110","title":"The YAGO-NAGA approach to knowledge discovery","display_name":"The YAGO-NAGA approach to knowledge discovery","publication_year":2009,"publication_date":"2009-03-20","ids":{"openalex":"https://openalex.org/W2006149654","doi":"https://doi.org/10.1145/1519103.1519110","mag":"2006149654"},"language":"en","primary_location":{"id":"doi:10.1145/1519103.1519110","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1519103.1519110","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"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":"ACM SIGMOD Record","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/A5024434748","display_name":"Gjergji Kasneci","orcid":null},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Gjergji Kasneci","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbruecken, Germany","Max-Planck Institute for Informatics, Saarbruecken, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbruecken, Germany","institution_ids":["https://openalex.org/I4210109712"]},{"raw_affiliation_string":"Max-Planck Institute for Informatics, Saarbruecken, Germany#TAB#","institution_ids":["https://openalex.org/I149899117"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055190394","display_name":"Maya Ramanath","orcid":"https://orcid.org/0000-0002-5413-5686"},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maya Ramanath","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbruecken, Germany","Max-Planck Institute for Informatics, Saarbruecken, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbruecken, Germany","institution_ids":["https://openalex.org/I4210109712"]},{"raw_affiliation_string":"Max-Planck Institute for Informatics, Saarbruecken, Germany#TAB#","institution_ids":["https://openalex.org/I149899117"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034994700","display_name":"Fabian M. Suchanek","orcid":"https://orcid.org/0000-0001-7189-2796"},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fabian Suchanek","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbruecken, Germany","Max-Planck Institute for Informatics, Saarbruecken, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbruecken, Germany","institution_ids":["https://openalex.org/I4210109712"]},{"raw_affiliation_string":"Max-Planck Institute for Informatics, Saarbruecken, Germany#TAB#","institution_ids":["https://openalex.org/I149899117"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088135366","display_name":"Gerhard Weikum","orcid":"https://orcid.org/0000-0003-4959-6098"},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Weikum","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbruecken, Germany","Max-Planck Institute for Informatics, Saarbruecken, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbruecken, Germany","institution_ids":["https://openalex.org/I4210109712"]},{"raw_affiliation_string":"Max-Planck Institute for Informatics, Saarbruecken, Germany#TAB#","institution_ids":["https://openalex.org/I149899117"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024434748"],"corresponding_institution_ids":["https://openalex.org/I149899117","https://openalex.org/I4210109712"],"apc_list":null,"apc_paid":null,"fwci":19.9212,"has_fulltext":false,"cited_by_count":104,"citation_normalized_percentile":{"value":0.99432455,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"37","issue":"4","first_page":"41","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9988999962806702,"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":0.848832368850708},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6561603546142578},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.6531262397766113},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.6050957441329956},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5354746580123901},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.4839087426662445},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4248393177986145},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3500882387161255},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2756599485874176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2240692377090454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.848832368850708},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6561603546142578},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.6531262397766113},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.6050957441329956},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5354746580123901},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.4839087426662445},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4248393177986145},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3500882387161255},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2756599485874176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2240692377090454},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1519103.1519110","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1519103.1519110","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"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":"ACM SIGMOD Record","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.167.8154","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.167.8154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://suchanek.name/work/publications/sigmodrec2008.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.211.6495","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.211.6495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sigmod.org/sigmod/record/issues/0812/p041.special.kasneci.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.133","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://domino.mpi-inf.mpg.de/intranet/ag5/ag5publ.nsf/AuthorEditorIndividualView/85a49a1e432c1149c125757a006ea760/$FILE/yago-approach-revised.pdf","raw_type":"text"},{"id":"pmh:oai:escidoc.org:escidoc:2032385","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0019-B5CE-F","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"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":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W57058802","https://openalex.org/W70368085","https://openalex.org/W102708294","https://openalex.org/W122707235","https://openalex.org/W1493490255","https://openalex.org/W1571315124","https://openalex.org/W1800049145","https://openalex.org/W1973483159","https://openalex.org/W2022166150","https://openalex.org/W2035266017","https://openalex.org/W2100408869","https://openalex.org/W2114544510","https://openalex.org/W2124067180","https://openalex.org/W2124943418","https://openalex.org/W2130766266","https://openalex.org/W2130878769","https://openalex.org/W2131381130","https://openalex.org/W2140636749","https://openalex.org/W2144416276","https://openalex.org/W2146304342","https://openalex.org/W2148540243","https://openalex.org/W2155737120","https://openalex.org/W2161563551","https://openalex.org/W2913389685"],"related_works":["https://openalex.org/W2900382651","https://openalex.org/W1981879262","https://openalex.org/W2363417484","https://openalex.org/W4225863708","https://openalex.org/W1480103567","https://openalex.org/W1599970036","https://openalex.org/W1849827364","https://openalex.org/W2003145209","https://openalex.org/W1850639582","https://openalex.org/W2115177975"],"abstract_inverted_index":{"This":[0],"paper":[1,96],"gives":[2],"an":[3],"overview":[4],"on":[5,83,131],"the":[6,43,59,65,98,101,119],"YAGO-NAGA":[7],"approach":[8,107],"to":[9,50,90,108],"information":[10],"extraction":[11],"for":[12,33,77,113,122],"building":[13],"a":[14],"conveniently":[15],"searchable,":[16],"large-scale,":[17],"highly":[18],"accurate":[19],"knowledge":[20,67],"base":[21,68],"of":[22,31,46,74,100],"common":[23],"facts.":[24],"YAGO":[25,66,102],"harvests":[26],"infoboxes":[27],"and":[28,38,58,115,118],"category":[29],"names":[30],"Wikipedia":[32],"facts":[34],"about":[35,70,78],"individual":[36],"entities,":[37],"it":[39],"reconciles":[40],"these":[41],"with":[42],"taxonomic":[44],"backbone":[45],"WordNet":[47],"in":[48],"order":[49],"ensure":[51],"that":[52],"all":[53],"entities":[54],"have":[55],"proper":[56],"classes":[57],"class":[60],"system":[61],"is":[62,88],"consistent.":[63],"Currently,":[64],"contains":[69],"19":[71],"million":[72,80],"instances":[73],"binary":[75],"relations":[76],"1.95":[79],"entities.":[81],"Based":[82],"intensive":[84],"sampling,":[85],"its":[86,105,111],"accuracy":[87],"estimated":[89],"be":[91],"above":[92],"95":[93],"percent.":[94],"The":[95],"presents":[97],"architecture":[99],"extractor":[103],"toolkit,":[104],"distinctive":[106],"consistency":[109],"checking,":[110],"provisions":[112],"maintenance":[114],"further":[116],"growth,":[117],"query":[120],"engine":[121],"YAGO,":[123],"coined":[124],"NAGA.":[125],"It":[126],"also":[127],"discusses":[128],"ongoing":[129],"work":[130],"extensions":[132],"towards":[133],"integrating":[134],"fact":[135],"candidates":[136],"extracted":[137],"from":[138],"natural-language":[139],"text":[140],"sources.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":21}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}