{"id":"https://openalex.org/W3094039038","doi":"https://doi.org/10.1145/3340531.3412781","title":"Profiling Entity Matching Benchmark Tasks","display_name":"Profiling Entity Matching Benchmark Tasks","publication_year":2020,"publication_date":"2020-10-19","ids":{"openalex":"https://openalex.org/W3094039038","doi":"https://doi.org/10.1145/3340531.3412781","mag":"3094039038"},"language":"en","primary_location":{"id":"doi:10.1145/3340531.3412781","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information &amp; 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/A5010968230","display_name":"Anna Primpeli","orcid":"https://orcid.org/0000-0002-1783-2482"},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Anna Primpeli","raw_affiliation_strings":["University of Mannheim, Mannheim, Germany"],"affiliations":[{"raw_affiliation_string":"University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076876024","display_name":"Christian Bizer","orcid":"https://orcid.org/0000-0003-2367-0237"},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Bizer","raw_affiliation_strings":["University of Mannheim, Mannheim, Germany"],"affiliations":[{"raw_affiliation_string":"University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010968230"],"corresponding_institution_ids":["https://openalex.org/I177802217"],"apc_list":null,"apc_paid":null,"fwci":2.6928,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.90658786,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3101","last_page":"3108"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9778000116348267,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9765999913215637,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7950209975242615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7890632748603821},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.7188972234725952},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6748325824737549},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4773578643798828},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4525453746318817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44740983843803406},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4360806941986084},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07959377765655518}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7950209975242615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7890632748603821},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.7188972234725952},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6748325824737549},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4773578643798828},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4525453746318817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44740983843803406},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4360806941986084},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07959377765655518},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3340531.3412781","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information &amp; Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:57249","is_oa":false,"landing_page_url":"https://madoc.bib.uni-mannheim.de/57249/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196315","display_name":"MADOC (University of Mannheim)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177802217","host_organization_name":"University of Mannheim","host_organization_lineage":["https://openalex.org/I177802217"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1547612978","https://openalex.org/W1981590391","https://openalex.org/W2073471108","https://openalex.org/W2107966677","https://openalex.org/W2114764731","https://openalex.org/W2415809604","https://openalex.org/W2474883156","https://openalex.org/W2798649495","https://openalex.org/W2944916929","https://openalex.org/W2946457832","https://openalex.org/W2947088031","https://openalex.org/W2951147191","https://openalex.org/W2957204582","https://openalex.org/W3007475739","https://openalex.org/W3010144884","https://openalex.org/W3080592272","https://openalex.org/W3097013020","https://openalex.org/W3099883947","https://openalex.org/W4251111867","https://openalex.org/W4255566164"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W2086519370","https://openalex.org/W2028665553","https://openalex.org/W2087343574","https://openalex.org/W2535915176","https://openalex.org/W2105860728","https://openalex.org/W4287657826"],"abstract_inverted_index":{"Entity":[0],"matching":[1,27,42,70,120,129,201],"is":[2,145],"a":[3,18,59,137],"central":[4,66],"task":[5],"in":[6,92],"data":[7],"integration":[8],"which":[9,64],"has":[10,29],"been":[11,30],"researched":[12],"for":[13,24,149,177],"decades.":[14],"Over":[15],"this":[16,144],"time,":[17],"wide":[19],"range":[20],"of":[21,61,68,78,89,117,128,161],"benchmark":[22,43,79,152,185],"tasks":[23,80,91,121,157,197],"evaluating":[25],"entity":[26,41],"methods":[28],"developed.":[31],"This":[32],"resource":[33],"paper":[34],"systematically":[35],"complements,":[36],"profiles,":[37],"and":[38,130,140,169,174,182,198],"compares":[39],"21":[40],"tasks.":[44,71],"In":[45,110],"order":[46,111],"to":[47,112,123,190,199],"better":[48],"understand":[49],"the":[50,69,87,90,114,147,171,184],"specific":[51],"challenges":[52],"associated":[53],"with":[54,105,158],"different":[55],"tasks,":[56,153,186],"we":[57,75,85,154,187],"define":[58],"set":[60],"profiling":[62,181],"dimensions":[63],"capture":[65],"aspects":[67],"Using":[72],"these":[73,156],"dimensions,":[74],"create":[76],"groups":[77],"having":[81],"similar":[82],"characteristics.":[83],"Afterwards,":[84],"assess":[86],"difficulty":[88],"each":[93],"group":[94],"by":[95],"computing":[96],"baseline":[97],"evaluation":[98,118],"results":[99],"using":[100],"standard":[101],"feature":[102],"engineering":[103],"together":[104],"two":[106],"common":[107],"classification":[108],"methods.":[109],"enable":[113],"exact":[115],"reproducibility":[116],"results,":[119],"need":[122],"contain":[124],"exactly":[125],"defined":[126,205],"sets":[127,160,176],"non-matching":[131,162],"record":[132],"pairs,":[133,163],"as":[134,136,164,166,193,195],"well":[135,165,194],"fixed":[138,159,167],"development":[139,173],"test":[141,175],"split.":[142],"As":[143],"not":[146],"case":[148],"some":[150],"widely-used":[151],"complement":[155],"splits,":[168],"provide":[170],"resulting":[172],"public":[178],"download.":[179],"By":[180],"complementing":[183],"support":[188],"researchers":[189],"select":[191],"challenging":[192],"diverse":[196],"compare":[200],"systems":[202],"on":[203],"clearly":[204],"grounds.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
