{"id":"https://openalex.org/W2546466160","doi":"https://doi.org/10.1109/tkde.2016.2623607","title":"QDA: A Query-Driven Approach to Entity Resolution","display_name":"QDA: A Query-Driven Approach to Entity Resolution","publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W2546466160","doi":"https://doi.org/10.1109/tkde.2016.2623607","mag":"2546466160"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2016.2623607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2016.2623607","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","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/A5072869590","display_name":"Hotham Altwaijry","orcid":null},"institutions":[{"id":"https://openalex.org/I1284598098","display_name":"King Abdulaziz City for Science and Technology","ror":"https://ror.org/05tdz6m39","country_code":"SA","type":"facility","lineage":["https://openalex.org/I1284598098"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Hotham Altwaijry","raw_affiliation_strings":["King Abdulaziz City for Science & Technology (KACST), Riyadh, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdulaziz City for Science & Technology (KACST), Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I1284598098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078774287","display_name":"Dmitri V. Kalashnikov","orcid":"https://orcid.org/0009-0002-4180-1384"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dmitri V. Kalashnikov","raw_affiliation_strings":["AT&T Labs Research, Florham Park, NJ"],"affiliations":[{"raw_affiliation_string":"AT&T Labs Research, Florham Park, NJ","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010114060","display_name":"Sharad Mehrotra","orcid":"https://orcid.org/0000-0003-1667-5435"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharad Mehrotra","raw_affiliation_strings":["University of California at Irvine, Irvine, CA"],"affiliations":[{"raw_affiliation_string":"University of California at Irvine, Irvine, CA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072869590"],"corresponding_institution_ids":["https://openalex.org/I1284598098"],"apc_list":null,"apc_paid":null,"fwci":1.4362,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85338933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"29","issue":"2","first_page":"402","last_page":"417"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9811999797821045,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9753999710083008,"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":0.8225690126419067},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.667691707611084},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6117607355117798},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5378396511077881},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5304225087165833},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.5300243496894836},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5136975049972534},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.4683629274368286},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4398260712623596},{"id":"https://openalex.org/keywords/spatial-query","display_name":"Spatial query","score":0.4185497760772705},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.41510283946990967},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39087313413619995},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3282255232334137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2893197536468506},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.24289143085479736},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16553106904029846},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.08019426465034485}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8225690126419067},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.667691707611084},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6117607355117798},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5378396511077881},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5304225087165833},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.5300243496894836},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5136975049972534},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.4683629274368286},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4398260712623596},{"id":"https://openalex.org/C172722865","wikidata":"https://www.wikidata.org/wiki/Q2302053","display_name":"Spatial query","level":5,"score":0.4185497760772705},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.41510283946990967},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39087313413619995},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3282255232334137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2893197536468506},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.24289143085479736},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16553106904029846},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.08019426465034485},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2016.2623607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2016.2623607","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1349182341","display_name":null,"funder_award_id":"CNS-1450768","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G257630244","display_name":null,"funder_award_id":"IIS-1527536","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G991520933","display_name":null,"funder_award_id":"CNS-1545071","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322997","display_name":"King Abdulaziz City for Science and Technology","ror":"https://ror.org/05tdz6m39"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W509898","https://openalex.org/W1502916507","https://openalex.org/W1547556487","https://openalex.org/W1547705211","https://openalex.org/W1559390933","https://openalex.org/W1612155886","https://openalex.org/W1782779125","https://openalex.org/W1964786778","https://openalex.org/W1975184797","https://openalex.org/W1993091968","https://openalex.org/W1994541786","https://openalex.org/W1997684383","https://openalex.org/W1998475090","https://openalex.org/W2012604221","https://openalex.org/W2024770506","https://openalex.org/W2032871318","https://openalex.org/W2034190452","https://openalex.org/W2036216970","https://openalex.org/W2040348939","https://openalex.org/W2046020929","https://openalex.org/W2052390074","https://openalex.org/W2073471108","https://openalex.org/W2074876483","https://openalex.org/W2087183379","https://openalex.org/W2102350406","https://openalex.org/W2107499437","https://openalex.org/W2108991785","https://openalex.org/W2123561513","https://openalex.org/W2139407700","https://openalex.org/W2140789797","https://openalex.org/W2148524305","https://openalex.org/W2169328499","https://openalex.org/W2220488081","https://openalex.org/W2914959486","https://openalex.org/W3146259567","https://openalex.org/W4230502578","https://openalex.org/W4254788633","https://openalex.org/W6629956336","https://openalex.org/W6633021001"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W3125756434","https://openalex.org/W2392799717","https://openalex.org/W2572349046","https://openalex.org/W1003283331","https://openalex.org/W2026738364","https://openalex.org/W2161787409","https://openalex.org/W2146885082","https://openalex.org/W2017989738","https://openalex.org/W2406556739"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,10,28,31,39,50,89],"problem":[4],"of":[5,12,30,45,53,70],"query-aware":[6],"data":[7,40],"cleaning":[8,41,54],"in":[9,33],"context":[11],"a":[13,20,61],"user":[14],"query.":[15],"In":[16],"particular,":[17],"we":[18],"develop":[19],"novel":[21],"Query-Driven":[22],"Approach":[23],"(QDA)":[24],"that":[25,56,76],"systematically":[26],"exploits":[27],"semantics":[29],"predicates":[32],"SQL-like":[34,63],"selection":[35,64],"queries":[36],"to":[37,48,59,83],"reduce":[38],"overhead.":[42],"The":[43,66],"objective":[44],"QDA":[46,71,78],"is":[47,77,79,91],"issue":[49],"minimum":[51],"number":[52],"steps":[55],"are":[57],"necessary":[58],"answer":[60],"given":[62],"correctly.":[65],"comprehensive":[67],"empirical":[68],"evaluation":[69],"demonstrates":[72],"outstanding":[73],"results":[74],"-":[75],"significantly":[80],"better":[81],"compared":[82],"traditional":[84],"ER":[85],"techniques,":[86],"especially":[87],"when":[88],"query":[90],"very":[92],"selective.":[93]},"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":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}