{"id":"https://openalex.org/W2947088031","doi":"https://doi.org/10.3233/sw-190356","title":"Learning expressive linkage rules from sparse data","display_name":"Learning expressive linkage rules from sparse data","publication_year":2019,"publication_date":"2019-05-28","ids":{"openalex":"https://openalex.org/W2947088031","doi":"https://doi.org/10.3233/sw-190356","mag":"2947088031"},"language":"en","primary_location":{"id":"doi:10.3233/sw-190356","is_oa":false,"landing_page_url":"https://doi.org/10.3233/sw-190356","pdf_url":null,"source":{"id":"https://openalex.org/S4210177235","display_name":"Semantic Web","issn_l":"1570-0844","issn":["1570-0844","2210-4968"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Semantic Web","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/A5018057749","display_name":"Petar Petrovski","orcid":null},"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":"Petar Petrovski","raw_affiliation_strings":["Data and Web Science Group, University of Mannheim, B6, 26, 68159 Mannheim, Germany. E-mails:\u00a0petar@informatik.uni-mannheim.de,\u00a0chris@informatik.uni-mannheim.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Web Science Group, University of Mannheim, B6, 26, 68159 Mannheim, Germany. E-mails:\u00a0petar@informatik.uni-mannheim.de,\u00a0chris@informatik.uni-mannheim.de","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":["Data and Web Science Group, University of Mannheim, B6, 26, 68159 Mannheim, Germany. E-mails:\u00a0petar@informatik.uni-mannheim.de,\u00a0chris@informatik.uni-mannheim.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Web Science Group, University of Mannheim, B6, 26, 68159 Mannheim, Germany. E-mails:\u00a0petar@informatik.uni-mannheim.de,\u00a0chris@informatik.uni-mannheim.de","institution_ids":["https://openalex.org/I177802217"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5018057749"],"corresponding_institution_ids":["https://openalex.org/I177802217"],"apc_list":null,"apc_paid":null,"fwci":1.0692,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78736771,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"11","issue":"3","first_page":"549","last_page":"567"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9799000024795532,"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":0.7592126727104187},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.6687065958976746},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5782163143157959},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5585917830467224},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5308060646057129},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.530238151550293},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5246301293373108},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4528237283229828},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.4442518353462219},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.4102931022644043},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39148569107055664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38184067606925964},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37245839834213257},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15338584780693054},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11850196123123169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7592126727104187},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.6687065958976746},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5782163143157959},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5585917830467224},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5308060646057129},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.530238151550293},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5246301293373108},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4528237283229828},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.4442518353462219},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4102931022644043},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39148569107055664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38184067606925964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37245839834213257},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15338584780693054},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11850196123123169},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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":2,"locations":[{"id":"doi:10.3233/sw-190356","is_oa":false,"landing_page_url":"https://doi.org/10.3233/sw-190356","pdf_url":null,"source":{"id":"https://openalex.org/S4210177235","display_name":"Semantic Web","issn_l":"1570-0844","issn":["1570-0844","2210-4968"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Semantic Web","raw_type":"journal-article"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:50552","is_oa":false,"landing_page_url":"https://content.iospress.com/articles/semantic-web/sw190356","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":"Zeitschriftenartikel"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4099999964237213,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W155236017","https://openalex.org/W178573792","https://openalex.org/W192652968","https://openalex.org/W1549099081","https://openalex.org/W1568705965","https://openalex.org/W1582775886","https://openalex.org/W1974758710","https://openalex.org/W1981578383","https://openalex.org/W1981590391","https://openalex.org/W1992329416","https://openalex.org/W1997927541","https://openalex.org/W1998901603","https://openalex.org/W2014964486","https://openalex.org/W2031250218","https://openalex.org/W2035615211","https://openalex.org/W2036216970","https://openalex.org/W2041439319","https://openalex.org/W2043437843","https://openalex.org/W2045968013","https://openalex.org/W2046020929","https://openalex.org/W2073471108","https://openalex.org/W2084413241","https://openalex.org/W2109553965","https://openalex.org/W2119225321","https://openalex.org/W2119320829","https://openalex.org/W2123561513","https://openalex.org/W2131744502","https://openalex.org/W2133236963","https://openalex.org/W2140527686","https://openalex.org/W2147218300","https://openalex.org/W2148019918","https://openalex.org/W2149956050","https://openalex.org/W2154785834","https://openalex.org/W2164456230","https://openalex.org/W2171472464","https://openalex.org/W2239873446","https://openalex.org/W2295639288","https://openalex.org/W2396717473","https://openalex.org/W2460313383","https://openalex.org/W2521135474","https://openalex.org/W2589049294","https://openalex.org/W2885625746","https://openalex.org/W2913519381","https://openalex.org/W3146259567","https://openalex.org/W4241727697","https://openalex.org/W6639924009"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W3024870410","https://openalex.org/W2410652950","https://openalex.org/W4380150146","https://openalex.org/W4283773154","https://openalex.org/W3139174110","https://openalex.org/W4289597203","https://openalex.org/W4321353415","https://openalex.org/W2950538088","https://openalex.org/W1977098485"],"abstract_inverted_index":{"A":[0],"central":[1,214],"problem":[2],"in":[3,14,17,23,103],"the":[4,7,29,46,138,189,193,198,213,217,239,266],"context":[5],"of":[6,9,38,45,94,144,152,164,216,233,250],"Web":[8],"Data":[10],"as":[11,13,79,81,107],"well":[12,80],"data":[15,25,57,89,98],"integration":[16],"general":[18],"is":[19,99],"to":[20,85,127,252,256,265,272,276,281],"identify":[21],"entities":[22],"different":[24,70],"sources":[26],"that":[27,58,123,200],"describe":[28,242],"same":[30],"real-world":[31],"object.":[32],"There":[33],"exists":[34],"a":[35,69,91,100,162],"large":[36,92],"body":[37],"research":[39,48],"on":[40,50,53,156,192,259],"entity":[41,51,120],"resolution.":[42],"Interestingly,":[43],"most":[44],"existing":[47],"focuses":[49],"resolution":[52,121],"dense":[54],"data,":[55,87],"meaning":[56],"does":[59],"not":[60],"contain":[61],"too":[62],"many":[63],"missing":[64,95,160,186,203],"values.":[65,96,204],"This":[66],"paper":[67],"sets":[68],"focus":[71],"and":[72,117,147,245,278],"explores":[73],"learning":[74],"expressive":[75,129],"linkage":[76,130],"rules":[77,84,131,146,150],"from":[78,132,161,185,188,202],"applying":[82],"these":[83,153],"sparse":[86,133],"i.e.":[88],"exhibiting":[90],"amount":[93],"Sparse":[97],"common":[101],"challenge":[102],"application":[104],"domains":[105],"such":[106],"e-commerce,":[108],"online":[109,113],"hotel":[110],"booking,":[111],"or":[112],"recruiting.":[114],"We":[115,224,247],"propose":[116,168],"compare":[118],"three":[119,232],"methods":[122,227],"employ":[124],"genetic":[125],"programming":[126],"learn":[128],"data.":[134],"First,":[135],"we":[136,167,206],"introduce":[137,207],"GenLinkGL":[139],"algorithm":[140,210],"which":[141,157,170,211],"learns":[142],"groups":[143,154],"matching":[145],"applies":[148],"specific":[149],"out":[151],"depending":[155],"values":[158],"are":[159,235],"pair":[163],"records.":[165],"Next,":[166],"GenLinkSA,":[169],"employs":[171],"selective":[172],"aggregation":[173],"operators":[174,178],"within":[175],"rules.":[176],"These":[177],"exclude":[179],"misleading":[180],"similarity":[181],"scores":[182],"(which":[183],"result":[184],"values)":[187],"aggregations,":[190],"but":[191],"other":[194,240],"hand":[195],"also":[196],"penalize":[197],"uncertainty":[199],"results":[201],"Finally,":[205],"GenLinkComb,":[208],"an":[209],"combines":[212],"ideas":[215],"previous":[218],"two":[219],"into":[220],"one":[221],"integrated":[222],"method.":[223],"evaluate":[225],"all":[226],"using":[228],"six":[229],"benchmark":[230],"datasets:":[231],"them":[234],"e-commerce":[236],"product":[237],"datasets,":[238],"datasets":[241],"restaurants,":[243],"movies,":[244],"drugs.":[246],"show":[248],"improvements":[249],"up":[251],"16%":[253],"F-measure":[254,262],"compared":[255,264,271,275,280],"handwritten":[257],"rules,":[258],"average":[260],"12%":[261],"improvement":[263],"original":[267],"GenLink":[268],"algorithm,":[269],"15%":[270],"EAGLE,":[273],"8%":[274],"FEBRL,":[277],"5%":[279],"CoSum-P.":[282]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}