{"id":"https://openalex.org/W2535778619","doi":"https://doi.org/10.1145/2983323.2983831","title":"Attribute-based Crowd Entity Resolution","display_name":"Attribute-based Crowd Entity Resolution","publication_year":2016,"publication_date":"2016-10-24","ids":{"openalex":"https://openalex.org/W2535778619","doi":"https://doi.org/10.1145/2983323.2983831","mag":"2535778619"},"language":"en","primary_location":{"id":"doi:10.1145/2983323.2983831","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983323.2983831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-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/A5039995971","display_name":"Asif Khan","orcid":"https://orcid.org/0000-0001-5009-3290"},"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":"Asif R. Khan","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","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, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039995971"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":2.9993,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.92948436,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"549","last_page":"558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","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/T10764","display_name":"Privacy-Preserving Technologies in Data","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/T11719","display_name":"Data Quality and Management","score":0.9987000226974487,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.8706633448600769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7773637771606445},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.7203129529953003},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.674003541469574},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6064417362213135},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5792037844657898},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.523363471031189},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5109414458274841},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.4866953194141388},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4599316418170929}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.8706633448600769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773637771606445},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.7203129529953003},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.674003541469574},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6064417362213135},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5792037844657898},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.523363471031189},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5109414458274841},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.4866953194141388},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4599316418170929},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2983323.2983831","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983323.2983831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W125094683","https://openalex.org/W1496255159","https://openalex.org/W1501025848","https://openalex.org/W1502916507","https://openalex.org/W1583345983","https://openalex.org/W1736726159","https://openalex.org/W1997321932","https://openalex.org/W2025721839","https://openalex.org/W2036216970","https://openalex.org/W2053653724","https://openalex.org/W2056748234","https://openalex.org/W2076357412","https://openalex.org/W2081193615","https://openalex.org/W2091858563","https://openalex.org/W2106675345","https://openalex.org/W2113878109","https://openalex.org/W2117539524","https://openalex.org/W2117974736","https://openalex.org/W2125943921","https://openalex.org/W2131565021","https://openalex.org/W2141634619","https://openalex.org/W2145492473","https://openalex.org/W2148019918","https://openalex.org/W2163051926","https://openalex.org/W2168144930","https://openalex.org/W2535778619"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W3207526114"],"abstract_inverted_index":{"We":[0,142,167],"study":[1],"the":[2,6,67,76,132,152],"problem":[3],"of":[4,16,21,60,69,95,134,156,177],"using":[5],"crowd":[7,71,77,186],"to":[8,100,130,150,161],"perform":[9],"entity":[10],"resolution":[11],"(ER)":[12],"on":[13,81,174],"a":[14,28,107,144,163,175],"set":[15],"records.":[17,61],"For":[18],"many":[19],"types":[20],"records,":[22,50,82],"especially":[23],"those":[24],"involving":[25],"images,":[26,179],"such":[27],"task":[29],"can":[30],"be":[31],"difficult":[32],"for":[33,38,46,57,78,86],"machines,":[34],"but":[35],"relatively":[36],"easy":[37],"humans.":[39],"Typical":[40],"crowd-based":[41,104],"ER":[42,72,187],"approaches":[43,73],"ask":[44],"workers":[45],"pairwise":[47,70,87],"judgments":[48,88],"between":[49,90],"which":[51,127,147,189],"quickly":[52],"becomes":[53,111],"prohibitively":[54],"expensive":[55],"even":[56,114],"moderate":[58],"numbers":[59],"In":[62],"this":[63],"paper,":[64],"we":[65,122],"reduce":[66],"cost":[68,140,197],"by":[74,103],"soliciting":[75],"attribute":[79,96,105],"labels":[80],"and":[83,180],"then":[84],"asking":[85],"only":[89],"records":[91],"with":[92,115,171],"similar":[93],"sets":[94],"labels.":[97],"However,":[98],"due":[99],"errors":[101],"induced":[102],"labeling,":[106],"naive":[108],"attribute-based":[109],"approach":[110,170],"extremely":[112],"inaccurate":[113],"few":[116],"attributes.":[117],"To":[118],"combat":[119],"these":[120],"errors,":[121],"use":[123],"error":[124,157],"mitigation":[125,158],"strategies":[126,159,188],"allow":[128],"us":[129,149],"control":[131],"accuracy":[133,192],"our":[135,169,183],"results":[136,184],"while":[137],"maintaining":[138],"significant":[139],"reductions.":[141],"develop":[143],"probabilistic":[145],"model":[146],"allows":[148],"determine":[151],"optimal,":[153],"lowest-cost":[154],"combination":[155],"needed":[160],"achieve":[162,190],"minimum":[164],"desired":[165],"accuracy.":[166],"test":[168],"actual":[172],"crowdworkers":[173],"dataset":[176],"celebrity":[178],"find":[181],"that":[182],"yield":[185],"high":[191],"yet":[193],"are":[194],"significantly":[195],"lower":[196],"than":[198],"pairwise-only":[199],"approaches.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}