{"id":"https://openalex.org/W2042913039","doi":"https://doi.org/10.14778/1920841.1920871","title":"Evaluating entity resolution results","display_name":"Evaluating entity resolution results","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W2042913039","doi":"https://doi.org/10.14778/1920841.1920871","mag":"2042913039"},"language":"en","primary_location":{"id":"doi:10.14778/1920841.1920871","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920871","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","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/A5084927411","display_name":"David Menestrina","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Menestrina","raw_affiliation_strings":["Stanford University, Stanford, CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012631773","display_name":"Steven Euijong Whang","orcid":"https://orcid.org/0000-0001-6419-931X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Euijong Whang","raw_affiliation_strings":["Stanford University, Stanford, CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055883336","display_name":"H\u00e9ctor Garc\u00eda-Molina","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hector Garcia-Molina","raw_affiliation_strings":["Stanford University, Stanford, CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084927411"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":8.0604,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.97323985,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"3","issue":"1-2","first_page":"208","last_page":"219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9904000163078308,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9879000186920166,"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/pairwise-comparison","display_name":"Pairwise comparison","score":0.7558408975601196},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.7406018376350403},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.6974042654037476},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6335931420326233},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5556471347808838},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5075474977493286},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.4512719511985779},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.42814257740974426},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42450448870658875},{"id":"https://openalex.org/keywords/distance-measures","display_name":"Distance measures","score":0.41816920042037964},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3841368854045868},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3649156987667084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3013387620449066},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.16053253412246704}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7558408975601196},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.7406018376350403},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6974042654037476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6335931420326233},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5556471347808838},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5075474977493286},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.4512719511985779},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.42814257740974426},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42450448870658875},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.41816920042037964},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3841368854045868},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3649156987667084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3013387620449066},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.16053253412246704}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/1920841.1920871","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920871","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.173.6066","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.173.6066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/%7Evldb2010/proceedings/files/papers/R18.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.469.3923","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.469.3923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umd.edu/class/spring2012/cmsc828L/Papers/MenestrinaVLDB10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W99972189","https://openalex.org/W162125039","https://openalex.org/W1490467549","https://openalex.org/W1532325895","https://openalex.org/W1559390933","https://openalex.org/W1569123402","https://openalex.org/W1585742040","https://openalex.org/W1860104593","https://openalex.org/W1979629649","https://openalex.org/W1989838421","https://openalex.org/W1991184411","https://openalex.org/W2007172042","https://openalex.org/W2009761865","https://openalex.org/W2010392031","https://openalex.org/W2024770506","https://openalex.org/W2036216970","https://openalex.org/W2046020929","https://openalex.org/W2051146966","https://openalex.org/W2067566391","https://openalex.org/W2111625757","https://openalex.org/W2112912553","https://openalex.org/W2117974736","https://openalex.org/W2123561513","https://openalex.org/W2129070834","https://openalex.org/W2129598390","https://openalex.org/W2135223301","https://openalex.org/W2141634619","https://openalex.org/W2141729166","https://openalex.org/W2148524305","https://openalex.org/W2154785834","https://openalex.org/W2159481891","https://openalex.org/W2161600801","https://openalex.org/W2164456230","https://openalex.org/W2171574281","https://openalex.org/W2426886874","https://openalex.org/W6676669657","https://openalex.org/W6678641665"],"related_works":["https://openalex.org/W2011472225","https://openalex.org/W2767338541","https://openalex.org/W3000057026","https://openalex.org/W3048565508","https://openalex.org/W3163984363","https://openalex.org/W2180288160","https://openalex.org/W2102177745","https://openalex.org/W2053556860","https://openalex.org/W2084461251","https://openalex.org/W2069148796"],"abstract_inverted_index":{"Entity":[0],"Resolution":[1],"(ER)":[2],"is":[3,133,166],"the":[4,14,58,90,114,135,150,176,199],"process":[5],"of":[6,9,92,117,131,152,164,170,206],"identifying":[7],"groups":[8],"records":[10],"that":[11,80,134,196,209],"refer":[12],"to":[13,40,51,147],"same":[15],"real-world":[16],"entity.":[17],"Various":[18],"measures":[19,38],"(e.g.,":[20],"pairwise":[21,179],"F":[22,26,180],"1":[23,27,181],",":[24],"cluster":[25,120],")":[28,111],"have":[29],"been":[30],"used":[31,178],"for":[32,57,103,138,202],"evaluating":[33],"ER":[34,37,77,93,104],"results.":[35],"However,":[36],"tend":[39],"be":[41,143,184],"chosen":[42],"in":[43],"an":[44,73,192],"ad-hoc":[45],"fashion":[46],"without":[47],"careful":[48],"thought":[49],"as":[50,124],"what":[52],"defines":[53],"a":[54,99,153,158,167,203],"good":[55],"result":[56],"specific":[59],"application":[60],"at":[61],"hand.":[62],"In":[63],"this":[64],"paper,":[65],"our":[66,171],"contributions":[67],"are":[68],"twofold.":[69],"First,":[70],"we":[71,97],"conduct":[72],"analysis":[74],"on":[75],"existing":[76],"measures,":[78],"showing":[79],"they":[81],"can":[82,142,183],"often":[83],"conflict":[84],"with":[85],"each":[86],"other":[87],"by":[88,113],"ranking":[89],"results":[91],"algorithms":[94],"differently.":[95],"Second,":[96],"explore":[98],"new":[100],"distance":[101,116],"measure":[102,161,182,201],"(called":[105],"\"generalized":[106],"merge":[107],"distance\"":[108],"or":[109],"GMD":[110,132,155,173,188,200],"inspired":[112],"edit":[115],"strings,":[118],"using":[119,187],"splits":[121,139],"and":[122,140,175],"merges":[123,141],"its":[125],"basic":[126],"operations.":[127],"A":[128],"significant":[129],"advantage":[130],"cost":[136,207],"functions":[137,208],"configured,":[144],"enabling":[145],"us":[146],"clearly":[148],"understand":[149],"characteristics":[151],"defined":[154],"measure.":[156],"Surprisingly,":[157],"state-of-the-art":[159],"clustering":[160],"called":[162],"Variation":[163],"Information":[165],"special":[168],"case":[169],"configurable":[172],"measure,":[174],"widely":[177],"directly":[185],"computed":[186],".":[189],"We":[190],"present":[191],"efficient":[193],"linear-time":[194],"algorithm":[195],"correctly":[197],"computes":[198],"large":[204],"class":[205],"satisfy":[210],"reasonable":[211],"properties.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"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":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}