{"id":"https://openalex.org/W2053653724","doi":"https://doi.org/10.14778/2536336.2536337","title":"Question selection for crowd entity resolution","display_name":"Question selection for crowd entity resolution","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W2053653724","doi":"https://doi.org/10.14778/2536336.2536337","mag":"2053653724"},"language":"en","primary_location":{"id":"doi:10.14778/2536336.2536337","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2536336.2536337","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/A5012631773","display_name":"Steven Euijong Whang","orcid":"https://orcid.org/0000-0001-6419-931X"},"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"]},{"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":"Steven Euijong Whang","raw_affiliation_strings":["Google Inc. and Stanford University"],"affiliations":[{"raw_affiliation_string":"Google Inc. and Stanford University","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058032177","display_name":"Peter Lofgren","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":"Peter Lofgren","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","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"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012631773"],"corresponding_institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":25.6069,"has_fulltext":false,"cited_by_count":151,"citation_normalized_percentile":{"value":0.99693744,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"6","issue":"6","first_page":"349","last_page":"360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9987000226974487,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9965999722480774,"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/crowdsourcing","display_name":"Crowdsourcing","score":0.9588220119476318},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8190998435020447},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.7361676692962646},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6263689994812012},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6216999292373657},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5919542908668518},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5720024108886719},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5121357440948486},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5055549144744873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49428534507751465},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.491699755191803},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45635488629341125},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43780872225761414},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33174145221710205},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32851871848106384},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21261873841285706},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.08960112929344177}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.9588220119476318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8190998435020447},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.7361676692962646},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6263689994812012},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6216999292373657},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5919542908668518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5720024108886719},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5121357440948486},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5055549144744873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49428534507751465},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.491699755191803},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45635488629341125},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43780872225761414},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33174145221710205},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32851871848106384},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21261873841285706},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.08960112929344177},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/2536336.2536337","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2536336.2536337","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:10.1.1.308.3778","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.3778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/vol6/p349-whang.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.686.6090","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.686.6090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://db.disi.unitn.eu/pages/VLDBProgram/pdf/research/p288-whang.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":23,"referenced_works":["https://openalex.org/W1492799879","https://openalex.org/W1595409123","https://openalex.org/W1977810318","https://openalex.org/W2024770506","https://openalex.org/W2025721839","https://openalex.org/W2053653724","https://openalex.org/W2056748234","https://openalex.org/W2068645020","https://openalex.org/W2069396035","https://openalex.org/W2098865355","https://openalex.org/W2108991785","https://openalex.org/W2113878109","https://openalex.org/W2116705992","https://openalex.org/W2119320829","https://openalex.org/W2145492473","https://openalex.org/W2148524305","https://openalex.org/W2168144930","https://openalex.org/W2169948249","https://openalex.org/W2295054684","https://openalex.org/W2295665070","https://openalex.org/W2914959486","https://openalex.org/W3146259567","https://openalex.org/W6681486618"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W1503094549","https://openalex.org/W4384486036","https://openalex.org/W135177976","https://openalex.org/W2337920774","https://openalex.org/W4318823662","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W3207526114","https://openalex.org/W4286908577"],"abstract_inverted_index":{"We":[0,63,102,149],"study":[1,64],"the":[2,10,16,24,47,65,127,131,136,172],"problem":[3,17,66],"of":[4,12,18,67,174],"enhancing":[5],"Entity":[6],"Resolution":[7],"(ER)":[8],"with":[9,70,130],"help":[11],"crowdsourcing.":[13],"ER":[14,82,108,117,167],"is":[15,90,94,139],"clustering":[19],"records":[20,69],"that":[21,109],"refer":[22,45],"to":[23,46,76,80,95,113,177],"same":[25,48],"real-world":[26],"entity":[27],"and":[28,125,157,160],"can":[29,50,110,164],"be":[30,51,111],"an":[31,58],"extremely":[32],"difficult":[33],"process":[34],"for":[35,55,61,107,146],"computer":[36],"algorithms":[37,154],"alone.":[38],"For":[39],"example,":[40],"figuring":[41],"out":[42],"which":[43],"images":[44],"person":[49],"a":[52,104],"hard":[53],"task":[54],"computers,":[56],"but":[57],"easy":[59],"one":[60],"humans.":[62,178],"resolving":[68],"crowdsourcing":[71],"where":[72],"we":[73,119,142,163],"ask":[74,96],"questions":[75,99,175],"humans":[77],"in":[78],"order":[79],"guide":[81],"into":[83],"producing":[84],"accurate":[85],"results.":[86],"Since":[87],"human":[88],"work":[89],"costly,":[91],"our":[92,151],"goal":[93],"as":[97,100],"few":[98],"possible.":[101],"propose":[103,143],"probabilistic":[105],"framework":[106],"used":[112],"estimate":[114],"how":[115,162],"much":[116],"accuracy":[118,138,168],"obtain":[120,165],"by":[121],"asking":[122],"each":[123],"question":[124,129,153],"select":[126],"best":[128,152],"highest":[132],"expected":[133,137],"accuracy.":[134],"Computing":[135],"#P-hard,":[140],"so":[141],"approximation":[144],"techniques":[145],"efficient":[147],"computation.":[148],"evaluate":[150],"on":[155],"real":[156],"synthetic":[158],"datasets":[159],"demonstrate":[161],"high":[166],"while":[169],"significantly":[170],"reducing":[171],"number":[173],"asked":[176]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":19},{"year":2015,"cited_by_count":22},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}