{"id":"https://openalex.org/W2083935441","doi":"https://doi.org/10.1145/2661829.2662073","title":"Canonicalizing Open Knowledge Bases","display_name":"Canonicalizing Open Knowledge Bases","publication_year":2014,"publication_date":"2014-11-03","ids":{"openalex":"https://openalex.org/W2083935441","doi":"https://doi.org/10.1145/2661829.2662073","mag":"2083935441"},"language":"en","primary_location":{"id":"doi:10.1145/2661829.2662073","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2661829.2662073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"preprint","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/A5081390951","display_name":"Luis Gal\u00e1rraga","orcid":"https://orcid.org/0000-0002-0241-5379"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Luis Gal\u00e1rraga","raw_affiliation_strings":["T\u00e9l\u00e9com ParisTech, Paris, France","Telecom-ParisTech, paris, France#TAB#"],"affiliations":[{"raw_affiliation_string":"T\u00e9l\u00e9com ParisTech, Paris, France","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"Telecom-ParisTech, paris, France#TAB#","institution_ids":["https://openalex.org/I12356871"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064343893","display_name":"Geremy Heitz","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geremy Heitz","raw_affiliation_strings":["Google Inc., Mountain View, CA, USA","Google Inc., Mountain View, CA USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002713363","display_name":"Kevin Murphy","orcid":"https://orcid.org/0000-0001-5196-7236"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Murphy","raw_affiliation_strings":["Google Inc., Mountain View, CA, USA","Google Inc., Mountain View, CA USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034994700","display_name":"Fabian M. Suchanek","orcid":"https://orcid.org/0000-0001-7189-2796"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fabian M. Suchanek","raw_affiliation_strings":["T\u00e9l\u00e9com ParisTech, Paris, France","Telecom-ParisTech, paris, France#TAB#"],"affiliations":[{"raw_affiliation_string":"T\u00e9l\u00e9com ParisTech, Paris, France","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"Telecom-ParisTech, paris, France#TAB#","institution_ids":["https://openalex.org/I12356871"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081390951"],"corresponding_institution_ids":["https://openalex.org/I12356871"],"apc_list":null,"apc_paid":null,"fwci":9.249,"has_fulltext":false,"cited_by_count":116,"citation_normalized_percentile":{"value":0.97921819,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1679","last_page":"1688"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9994999766349792,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7782819271087646},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6116273403167725},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5155918002128601},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.479190468788147},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.46801555156707764},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.44749873876571655},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.4294894337654114},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.41792604327201843},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34102916717529297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3334716558456421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782819271087646},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6116273403167725},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5155918002128601},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.479190468788147},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.46801555156707764},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.44749873876571655},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.4294894337654114},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.41792604327201843},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34102916717529297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3334716558456421}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2661829.2662073","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2661829.2662073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01699884v1","is_oa":false,"landing_page_url":"https://imt.hal.science/hal-01699884","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CIKM, Nov 2014, Shanghai, France. ⟨10.1145/2661829.2662073⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W23533901","https://openalex.org/W102708294","https://openalex.org/W1480376833","https://openalex.org/W1483236033","https://openalex.org/W1493490255","https://openalex.org/W1512387364","https://openalex.org/W1529731474","https://openalex.org/W1532325895","https://openalex.org/W1731062554","https://openalex.org/W1942169943","https://openalex.org/W1992930793","https://openalex.org/W2016753842","https://openalex.org/W2022166150","https://openalex.org/W2036216970","https://openalex.org/W2046020929","https://openalex.org/W2048455931","https://openalex.org/W2091950909","https://openalex.org/W2094728533","https://openalex.org/W2109215439","https://openalex.org/W2113227740","https://openalex.org/W2129842875","https://openalex.org/W2135451108","https://openalex.org/W2139346960","https://openalex.org/W2151048449","https://openalex.org/W2151502664","https://openalex.org/W2159882563","https://openalex.org/W2161494021","https://openalex.org/W2167187514","https://openalex.org/W2168185617","https://openalex.org/W2471366537","https://openalex.org/W3036621889","https://openalex.org/W3098991821"],"related_works":["https://openalex.org/W2382915105","https://openalex.org/W1520100787","https://openalex.org/W4292070284","https://openalex.org/W2016355461","https://openalex.org/W2620787630","https://openalex.org/W4319071221","https://openalex.org/W4313174091","https://openalex.org/W1533009136","https://openalex.org/W2159419920","https://openalex.org/W2329252456"],"abstract_inverted_index":{"Open":[0,68],"information":[1],"extraction":[2],"approaches":[3],"have":[4],"led":[5],"to":[6,31],"the":[7,14],"creation":[8],"of":[9,49],"large":[10],"knowledge":[11],"bases":[12],"from":[13],"Web.":[15],"The":[16],"problem":[17],"with":[18],"such":[19,67],"methods":[20,63],"is":[21],"that":[22,64],"their":[23],"entities":[24],"and":[25,33,46,75],"relations":[26],"are":[27],"not":[28],"canonicalized,":[29],"leading":[30],"redundant":[32],"ambiguous":[34],"facts.":[35],"For":[36],"example,":[37],"they":[38],"may":[39],"store":[40],"{Barack":[41],"Obama,":[42],"was":[43],"born,":[44],"Honolulu":[45],"{Obama,":[47],"place":[48],"birth,":[50],"Honolulu}.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"present":[56],"an":[57],"approach":[58],"based":[59],"on":[60],"machine":[61],"learning":[62],"can":[65],"canonicalize":[66],"IE":[69],"triples,":[70],"by":[71],"clustering":[72],"synonymous":[73],"names":[74],"phrases.":[76]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}