{"id":"https://openalex.org/W4389609719","doi":"https://doi.org/10.1145/3626763","title":"Splitting Tuples of Mismatched Entities","display_name":"Splitting Tuples of Mismatched Entities","publication_year":2023,"publication_date":"2023-12-08","ids":{"openalex":"https://openalex.org/W4389609719","doi":"https://doi.org/10.1145/3626763"},"language":"en","primary_location":{"id":"doi:10.1145/3626763","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626763","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626763","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3626763","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070565287","display_name":"Wenfei Fan","orcid":"https://orcid.org/0000-0001-5149-2656"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenfei Fan","raw_affiliation_strings":["Beihang University & Shenzhen Institute of Computing Sciences & University of Edinburgh, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University & Shenzhen Institute of Computing Sciences & University of Edinburgh, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011396023","display_name":"Ziyan Han","orcid":"https://orcid.org/0000-0002-6614-3755"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyan Han","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100738054","display_name":"Weilong Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weilong Ren","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006464523","display_name":"Ding Wang","orcid":"https://orcid.org/0009-0007-2937-4590"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068930286","display_name":"Yaoshu Wang","orcid":"https://orcid.org/0000-0002-5760-5145"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoshu Wang","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031241828","display_name":"Min Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Xie","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002103818","display_name":"Mengyi Yan","orcid":"https://orcid.org/0009-0006-9991-0267"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyi Yan","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5070565287"],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.745,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75927553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"1","issue":"4","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9939000010490417,"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/T10028","display_name":"Topic Modeling","score":0.9754999876022339,"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/tuple","display_name":"Tuple","score":0.9598903656005859},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6353302597999573},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5699606537818909},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.46630847454071045},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4412339925765991},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.43697136640548706},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4046802222728729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3108859956264496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2914174795150757},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.14388525485992432}],"concepts":[{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.9598903656005859},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6353302597999573},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5699606537818909},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.46630847454071045},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4412339925765991},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.43697136640548706},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4046802222728729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3108859956264496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2914174795150757},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.14388525485992432},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626763","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626763","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626763","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3626763","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626763","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626763","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1477544716","display_name":null,"funder_award_id":"Guangdong","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4488680036","display_name":null,"funder_award_id":"2022A15","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4690067854","display_name":null,"funder_award_id":"62202313","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5128870598","display_name":null,"funder_award_id":"62202313, 62225202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6106196308","display_name":null,"funder_award_id":"51501012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7680757266","display_name":null,"funder_award_id":"2022A1515010120","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G8128231151","display_name":null,"funder_award_id":"62225202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8513333314","display_name":null,"funder_award_id":"2021ZD01","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389609719.pdf","grobid_xml":"https://content.openalex.org/works/W4389609719.grobid-xml"},"referenced_works_count":85,"referenced_works":["https://openalex.org/W1488893975","https://openalex.org/W1981590391","https://openalex.org/W1985239372","https://openalex.org/W2022166150","https://openalex.org/W2026147624","https://openalex.org/W2059554611","https://openalex.org/W2077518845","https://openalex.org/W2081186682","https://openalex.org/W2094728533","https://openalex.org/W2100986433","https://openalex.org/W2107966677","https://openalex.org/W2119320829","https://openalex.org/W2159024459","https://openalex.org/W2164618618","https://openalex.org/W2164625277","https://openalex.org/W2169940602","https://openalex.org/W2171332293","https://openalex.org/W2502658919","https://openalex.org/W2569536984","https://openalex.org/W2591700809","https://openalex.org/W2767681556","https://openalex.org/W2775696413","https://openalex.org/W2794573079","https://openalex.org/W2798649495","https://openalex.org/W2803109423","https://openalex.org/W2885711033","https://openalex.org/W2886633187","https://openalex.org/W2895570208","https://openalex.org/W2897574832","https://openalex.org/W2901288224","https://openalex.org/W2942740455","https://openalex.org/W2943501111","https://openalex.org/W2946504770","https://openalex.org/W2951565755","https://openalex.org/W2957204582","https://openalex.org/W2962869320","https://openalex.org/W2964226158","https://openalex.org/W2966720878","https://openalex.org/W2970641574","https://openalex.org/W2974737854","https://openalex.org/W2997919412","https://openalex.org/W2998702515","https://openalex.org/W3000214033","https://openalex.org/W3004034804","https://openalex.org/W3004507689","https://openalex.org/W3005822199","https://openalex.org/W3006713198","https://openalex.org/W3011807731","https://openalex.org/W3013103751","https://openalex.org/W3014705052","https://openalex.org/W3015738839","https://openalex.org/W3021217443","https://openalex.org/W3029269967","https://openalex.org/W3029621839","https://openalex.org/W3029701880","https://openalex.org/W3030496122","https://openalex.org/W3030713612","https://openalex.org/W3032627613","https://openalex.org/W3035623224","https://openalex.org/W3040722616","https://openalex.org/W3082197983","https://openalex.org/W3098444442","https://openalex.org/W3103513278","https://openalex.org/W3105771849","https://openalex.org/W3106020963","https://openalex.org/W3123375411","https://openalex.org/W3133676199","https://openalex.org/W3164439293","https://openalex.org/W3169654496","https://openalex.org/W3173307842","https://openalex.org/W3173807324","https://openalex.org/W3174588372","https://openalex.org/W3174697924","https://openalex.org/W3175414801","https://openalex.org/W3197468999","https://openalex.org/W3197847098","https://openalex.org/W3198445485","https://openalex.org/W3210543059","https://openalex.org/W4206065759","https://openalex.org/W4210394794","https://openalex.org/W4281879035","https://openalex.org/W4289533900","https://openalex.org/W4289533994","https://openalex.org/W4299726479","https://openalex.org/W6772013027"],"related_works":["https://openalex.org/W4245395944","https://openalex.org/W2143551613","https://openalex.org/W1979740464","https://openalex.org/W2143345456","https://openalex.org/W2138823233","https://openalex.org/W1789991335","https://openalex.org/W2562731034","https://openalex.org/W4315705795","https://openalex.org/W2101053337","https://openalex.org/W1870651561"],"abstract_inverted_index":{"There":[0],"has":[1],"been":[2],"a":[3,44,60,90],"host":[4],"of":[5,25,46,92],"work":[6],"on":[7,168],"entity":[8],"resolution":[9],"(ER),":[10],"to":[11,16,27,30,62,66,71,79,136],"identify":[12,28],"tuples":[13,29,42,65,70],"that":[14,158],"refer":[15],"the":[17,23,54,80,126,129,148,159],"same":[18],"entity.":[19,51],"This":[20],"paper":[21],"studies":[22],"inverse":[24],"ER,":[26],"which":[31,94],"distinct":[32],"real-world":[33],"entities":[34,99],"are":[35],"matched":[36],"by":[37,124],"mistake,":[38],"and":[39,68,83,102,110,121,140,163],"split":[40,67,81],"such":[41],"into":[43],"set":[45],"tuples,":[47,82],"one":[48],"for":[49,97,147],"each":[50],"We":[52,58,131,144],"formulate":[53],"tuple":[55,149],"splitting":[56,150],"problem.":[57],"propose":[59],"scheme":[61,88,160],"decide":[63],"what":[64,69],"correct":[72],"without":[73],"splitting,":[74],"fix":[75],"errors/assign":[76],"attribute":[77,138],"values":[78],"impute":[84],"missing":[85,142],"values.":[86,143],"The":[87],"introduces":[89],"class":[91],"rules,":[93],"embed":[95],"predicates":[96],"aligning":[98],"across":[100],"relations":[101],"knowledge":[103],"graphs":[104],"G,":[105],"assessing":[106],"correlation":[107,119,139],"between":[108],"attributes,":[109],"extracting":[111],"data":[112,122,127],"from":[113],"G.":[114],"It":[115],"unifies":[116],"logic":[117],"deduction,":[118],"models,":[120],"extraction":[123],"chasing":[125],"with":[128,165],"rules.":[130],"train":[132],"machine":[133],"learning":[134],"models":[135],"assess":[137],"predict":[141],"develop":[145],"algorithms":[146],"scheme.":[151],"Using":[152],"real-life":[153],"data,":[154],"we":[155],"empirically":[156],"verify":[157],"is":[161],"efficient":[162],"accurate,":[164],"F-measure":[166],"0.92":[167],"average.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}