{"id":"https://openalex.org/W3174836606","doi":"https://doi.org/10.14778/3467861.3467878","title":"Dual-objective fine-tuning of BERT for entity matching","display_name":"Dual-objective fine-tuning of BERT for entity matching","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3174836606","doi":"https://doi.org/10.14778/3467861.3467878","mag":"3174836606"},"language":"en","primary_location":{"id":"doi:10.14778/3467861.3467878","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3467861.3467878","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":true,"oa_status":"green","oa_url":"https://madoc.bib.uni-mannheim.de/59958/1/p1913-peeters.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082603069","display_name":"Ralph Peeters","orcid":"https://orcid.org/0000-0003-3174-2616"},"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":"Ralph Peeters","raw_affiliation_strings":["University of Mannheim, Mannheim, Germany"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177802217"],"apc_list":null,"apc_paid":null,"fwci":7.1196,"has_fulltext":true,"cited_by_count":68,"citation_normalized_percentile":{"value":0.97469152,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"14","issue":"10","first_page":"1913","last_page":"1921"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9988999962806702,"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":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.983299970626831,"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":0.8394680023193359},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.7944444417953491},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5974191427230835},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.572136402130127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.515084445476532},{"id":"https://openalex.org/keywords/unique-identifier","display_name":"Unique identifier","score":0.49831724166870117},{"id":"https://openalex.org/keywords/numbering","display_name":"Numbering","score":0.49701645970344543},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.46354955434799194},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44089120626449585},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.4385102093219757},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43663284182548523},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4295431673526764},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36466044187545776},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.1406119465827942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8394680023193359},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7944444417953491},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5974191427230835},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.572136402130127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.515084445476532},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.49831724166870117},{"id":"https://openalex.org/C191916993","wikidata":"https://www.wikidata.org/wiki/Q362019","display_name":"Numbering","level":2,"score":0.49701645970344543},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.46354955434799194},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44089120626449585},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4385102093219757},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43663284182548523},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4295431673526764},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36466044187545776},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.1406119465827942},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3467861.3467878","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3467861.3467878","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:ub-madoc.bib.uni-mannheim.de:59958","is_oa":true,"landing_page_url":null,"pdf_url":"https://madoc.bib.uni-mannheim.de/59958/1/p1913-peeters.pdf","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":{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:59958","is_oa":true,"landing_page_url":null,"pdf_url":"https://madoc.bib.uni-mannheim.de/59958/1/p1913-peeters.pdf","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"},"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3174836606.pdf","grobid_xml":"https://content.openalex.org/works/W3174836606.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W1547612978","https://openalex.org/W2073471108","https://openalex.org/W2101234009","https://openalex.org/W2108991785","https://openalex.org/W2282821441","https://openalex.org/W2542998387","https://openalex.org/W2595551253","https://openalex.org/W2624871570","https://openalex.org/W2626778328","https://openalex.org/W2798649495","https://openalex.org/W2807329228","https://openalex.org/W2896457183","https://openalex.org/W2913340405","https://openalex.org/W2914526845","https://openalex.org/W2945883855","https://openalex.org/W2946123203","https://openalex.org/W2951660660","https://openalex.org/W2957204582","https://openalex.org/W2963121782","https://openalex.org/W2963854351","https://openalex.org/W2964121744","https://openalex.org/W2965373594","https://openalex.org/W2970102549","https://openalex.org/W2970971581","https://openalex.org/W2975059944","https://openalex.org/W2979826702","https://openalex.org/W2996428491","https://openalex.org/W2997591727","https://openalex.org/W3010144884","https://openalex.org/W3013840636","https://openalex.org/W3014705052","https://openalex.org/W3025624935","https://openalex.org/W3035231859","https://openalex.org/W3035579820","https://openalex.org/W3080592272","https://openalex.org/W3092962901","https://openalex.org/W3093671642","https://openalex.org/W3097384126","https://openalex.org/W3098824823","https://openalex.org/W3099883947","https://openalex.org/W3123375411","https://openalex.org/W3155638005","https://openalex.org/W3187798969"],"related_works":["https://openalex.org/W2413568490","https://openalex.org/W1913624564","https://openalex.org/W3130054399","https://openalex.org/W4301062032","https://openalex.org/W2343500026","https://openalex.org/W2319837024","https://openalex.org/W2390627310","https://openalex.org/W2033159440","https://openalex.org/W2413664130","https://openalex.org/W2051731675"],"abstract_inverted_index":{"An":[0],"increasing":[1],"number":[2],"of":[3,40,92,102,122,211,216,237,271,283],"data":[4,29,198,249],"providers":[5],"have":[6],"adopted":[7],"shared":[8,32],"numbering":[9],"schemes":[10],"such":[11,48],"as":[12,76,111,229,231],"GTIN,":[13],"ISBN,":[14],"DUNS,":[15],"or":[16],"ORCID":[17],"numbers":[18],"for":[19,28,37,53,65,95,119,131,150,181,201,250,265],"identifying":[20,120],"entities":[21],"in":[22,57,154,158],"the":[23,41,71,96,143,147,161,178,212,217,254,280,284],"respective":[24],"domain.":[25],"This":[26,241],"means":[27],"integration":[30],"that":[31,173,195,244,291],"identifiers":[33,49,69,75],"are":[34,50,294],"often":[35],"available":[36,52,200],"a":[38,63,86,112,127,155,208,235,269],"subset":[39],"entity":[42,66,72,93,99,148,152,168],"descriptions":[43,67,73,94,101,121],"to":[44,61,145,160,186,190,206,223,303],"be":[45,82,109],"integrated":[46],"while":[47,262],"not":[51],"others.":[54],"The":[55,79,105],"challenge":[56],"these":[58],"settings":[59],"is":[60,199],"learn":[62],"matcher":[64],"without":[68],"using":[70],"containing":[74],"training":[77,129,156,175,197,248],"data.":[78],"task":[80,106],"can":[81,107,176],"approached":[83],"by":[84,116,184],"learning":[85,117,287],"binary":[87,137],"classifier":[88],"which":[89,135],"distinguishes":[90],"pairs":[91],"same":[97],"real-world":[98],"from":[100],"different":[103,285],"entities.":[104,124],"also":[108],"modeled":[110],"multi-class":[113,140],"classification":[114],"problem":[115],"classifiers":[118],"individual":[123],"We":[125],"present":[126],"dual-objective":[128,174],"method":[130],"BERT,":[132],"called":[133],"JointBERT,":[134,245],"combines":[136],"matching":[138,169,179,227,239,281],"and":[139,214,274,289],"classification,":[141],"forcing":[142],"model":[144],"predict":[146],"identifier":[149],"each":[151],"description":[153],"pair":[157],"addition":[159],"match/non-match":[162],"decision.":[163],"Our":[164],"evaluation":[165,242],"across":[166],"five":[167],"benchmark":[170],"datasets":[171],"shows":[172,243],"increase":[177],"performance":[180],"seen":[182,260],"products":[183],"1%":[185],"5%":[187],"F1":[188],"compared":[189,302],"single-objective":[191],"Transformer-based":[192],"methods,":[193],"given":[194,246],"enough":[196,247],"both":[202,251],"objectives.":[203],"In":[204],"order":[205],"gain":[207],"deeper":[209],"understanding":[210],"strengths":[213],"weaknesses":[215],"proposed":[218],"method,":[219],"we":[220,278],"compare":[221],"JointBERT":[222],"several":[224],"other":[225,255],"BERT-based":[226,292],"methods":[228,256],"well":[230],"baseline":[232],"systems":[233],"along":[234],"set":[236],"specific":[238],"challenges.":[240],"objectives,":[252],"outperforms":[253],"on":[257,298],"tasks":[258],"involving":[259],"products,":[261],"it":[263],"underperforms":[264],"unseen":[266],"products.":[267],"Using":[268],"combination":[270],"LIME":[272],"explanations":[273],"domain-specific":[275],"word":[276,300],"classes,":[277],"analyze":[279],"decisions":[282],"deep":[286],"models":[288,293],"conclude":[290],"better":[295],"at":[296],"focusing":[297],"relevant":[299],"classes":[301],"RNN-based":[304],"models.":[305]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}