{"id":"https://openalex.org/W2065398649","doi":"https://doi.org/10.1145/2487575.2506179","title":"Entity resolution for big data","display_name":"Entity resolution for big data","publication_year":2013,"publication_date":"2013-08-11","ids":{"openalex":"https://openalex.org/W2065398649","doi":"https://doi.org/10.1145/2487575.2506179","mag":"2065398649"},"language":"en","primary_location":{"id":"doi:10.1145/2487575.2506179","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2487575.2506179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5086169451","display_name":"Lise Getoor","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lise Getoor","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018314576","display_name":"Ashwin Machanavajjhala","orcid":"https://orcid.org/0000-0003-1555-7330"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashwin Machanavajjhala","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1527","last_page":"1527"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9886999726295471,"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/T10028","display_name":"Topic Modeling","score":0.9847999811172485,"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":0.8599991202354431},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.7612006068229675},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6757085919380188},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5946935415267944},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5887178182601929},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5637316703796387},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5588088035583496},{"id":"https://openalex.org/keywords/information-overload","display_name":"Information overload","score":0.44701823592185974},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.44540467858314514},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.4302319884300232},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.4265189468860626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4141910672187805},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.38219571113586426},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2694130837917328},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.25809329748153687},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.25550997257232666},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.1616465449333191}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8599991202354431},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.7612006068229675},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6757085919380188},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5946935415267944},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5887178182601929},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5637316703796387},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5588088035583496},{"id":"https://openalex.org/C186625053","wikidata":"https://www.wikidata.org/wiki/Q1130191","display_name":"Information overload","level":2,"score":0.44701823592185974},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.44540467858314514},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4302319884300232},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.4265189468860626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4141910672187805},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.38219571113586426},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2694130837917328},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25809329748153687},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25550997257232666},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.1616465449333191},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2487575.2506179","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2487575.2506179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"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":0,"referenced_works":[],"related_works":["https://openalex.org/W3015724364","https://openalex.org/W4288263119","https://openalex.org/W2967994095","https://openalex.org/W2900126711","https://openalex.org/W4285240985","https://openalex.org/W4225162083","https://openalex.org/W2542958340","https://openalex.org/W3202115945","https://openalex.org/W4286930972","https://openalex.org/W1991374750"],"abstract_inverted_index":{"Entity":[0],"resolution":[1,37,87,124],"(ER),":[2],"the":[3,53,76,81,156,190],"problem":[4],"of":[5,46,56,67,71,78,100,128,147,151,162,182],"extracting,":[6],"matching":[7],"and":[8,14,31,34,49,69,96,107,137,159,170,187,202,206],"resolving":[9],"entity":[10,36,59,86,123],"mentions":[11],"in":[12,21,42,75,142],"structured":[13],"unstructured":[15],"data,":[16,80,98],"is":[17,62,88],"a":[18,43,64,126,145,148,179],"long-standing":[19],"challenge":[20],"database":[22],"management,":[23],"information":[24,132],"retrieval,":[25,133],"machine":[26,138],"learning,":[27,139],"natural":[28,134],"language":[29,135],"processing":[30,136],"statistics.":[32],"Accurate":[33],"fast":[35],"has":[38],"huge":[39],"practical":[40,157],"implications":[41],"wide":[44],"variety":[45,127],"commercial,":[47],"scientific":[48],"security":[50],"domains.":[51],"Despite":[52],"long":[54],"history":[55],"work":[57],"on":[58,122],"resolution,":[60],"there":[61],"still":[63],"surprising":[65],"diversity":[66],"approaches,":[68],"lack":[70],"guiding":[72],"theory.":[73],"Meanwhile,":[74],"age":[77],"big":[79],"need":[82],"for":[83],"high":[84],"quality":[85],"growing,":[89],"as":[90,198],"we":[91,118],"are":[92],"inundated":[93],"with":[94],"more":[95,97],"all":[99],"which":[101],"needs":[102],"to":[103,140,176],"be":[104,113],"integrated,":[105],"aligned":[106],"matched,":[108],"before":[109],"further":[110],"utility":[111],"can":[112],"extracted.":[114],"In":[115,174],"this":[116],"tutorial,":[117],"bring":[119],"together":[120],"perspectives":[121],"from":[125],"fields,":[129],"including":[130],"databases,":[131],"provide,":[141],"one":[143],"setting,":[144],"survey":[146],"large":[149],"body":[150],"work.":[152],"We":[153,164],"discuss":[154],"both":[155],"aspects":[158],"theoretical":[160],"underpinnings":[161],"ER.":[163,208],"describe":[165],"existing":[166,183],"solutions,":[167],"current":[168],"challenges":[169],"open":[171],"research":[172,195],"problems.":[173],"addition":[175],"giving":[177],"attendees":[178],"thorough":[180],"understanding":[181],"ER":[184],"models,":[185],"algorithms":[186],"evaluation":[188],"methods,":[189],"tutorial":[191],"will":[192],"cover":[193],"important":[194],"topics":[196],"such":[197],"scalable":[199],"ER,":[200,205],"active":[201],"lightly":[203],"supervised":[204],"query-driven":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}