{"id":"https://openalex.org/W4283314192","doi":"https://doi.org/10.14778/3529337.3529356","title":"Analyzing how BERT performs entity matching","display_name":"Analyzing how BERT performs entity matching","publication_year":2022,"publication_date":"2022-04-01","ids":{"openalex":"https://openalex.org/W4283314192","doi":"https://doi.org/10.14778/3529337.3529356"},"language":"en","primary_location":{"id":"doi:10.14778/3529337.3529356","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3529337.3529356","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://hdl.handle.net/11380/1290744","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037298798","display_name":"Matteo Paganelli","orcid":"https://orcid.org/0000-0001-8119-895X"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Matteo Paganelli","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063748915","display_name":"Francesco Del Buono","orcid":"https://orcid.org/0000-0003-0024-2563"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Del Buono","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005118555","display_name":"Andrea Baraldi","orcid":"https://orcid.org/0000-0002-1015-5490"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Baraldi","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005665643","display_name":"Francesco Guerra","orcid":"https://orcid.org/0000-0001-6864-568X"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Guerra","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037298798"],"corresponding_institution_ids":["https://openalex.org/I122346577"],"apc_list":null,"apc_paid":null,"fwci":3.729,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.9354766,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"15","issue":"8","first_page":"1726","last_page":"1738"},"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/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9836999773979187,"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":0.8465249538421631},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6660171151161194},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5647167563438416},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4927513897418976},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48283371329307556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47147467732429504},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.4533117115497589},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4166557192802429},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41411030292510986},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3493359088897705},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.13948646187782288},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11935558915138245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8465249538421631},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6660171151161194},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5647167563438416},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4927513897418976},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48283371329307556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47147467732429504},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4533117115497589},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4166557192802429},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41411030292510986},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3493359088897705},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.13948646187782288},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11935558915138245},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/3529337.3529356","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3529337.3529356","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:iris.unimore.it:11380/1290744","is_oa":true,"landing_page_url":"https://hdl.handle.net/11380/1290744","pdf_url":null,"source":{"id":"https://openalex.org/S4377196326","display_name":"Iris Unimore (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:iris.unimore.it:11380/1291984","is_oa":true,"landing_page_url":"https://hdl.handle.net/11380/1291984","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:iris.unimore.it:11380/1290744","is_oa":true,"landing_page_url":"https://hdl.handle.net/11380/1290744","pdf_url":null,"source":{"id":"https://openalex.org/S4377196326","display_name":"Iris Unimore (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2493916176","https://openalex.org/W2798649495","https://openalex.org/W3011807731","https://openalex.org/W3014705052","https://openalex.org/W3034503989","https://openalex.org/W3116527904","https://openalex.org/W3118485687","https://openalex.org/W3123375411","https://openalex.org/W3155638005","https://openalex.org/W3174836606","https://openalex.org/W3197468999","https://openalex.org/W4289671153"],"related_works":["https://openalex.org/W3140537242","https://openalex.org/W4311809271","https://openalex.org/W2130023876","https://openalex.org/W1972035260","https://openalex.org/W2188227831","https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W2551598679","https://openalex.org/W2012019886","https://openalex.org/W2166090428"],"abstract_inverted_index":{"State-of-the-art":[0],"Entity":[1],"Matching":[2],"(EM)":[3],"approaches":[4],"rely":[5],"on":[6,117],"transformer":[7],"architectures,":[8],"such":[9],"as":[10,47],"BERT":[11,77,110],",":[12],"for":[13,49],"generating":[14],"highly":[15],"contex-tualized":[16],"embeddings":[17,21],"of":[18,29,70,73,108,122,131,139,151],"terms.":[19],"The":[20,84],"are":[22,93,137],"then":[23],"used":[24],"to":[25,33,42,80,99,120],"predict":[26],"whether":[27],"pairs":[28,138],"entity":[30,140],"descriptions":[31,121,141],"refer":[32],"the":[34,50,57,71,95,100,105,109,128,132,147],"same":[35],"real-world":[36],"entity.":[37],"BERT-based":[38,160],"EM":[39,82,101,133,161],"models":[40],"demonstrated":[41],"be":[43],"effective,":[44],"but":[45,112],"act":[46],"black-boxes":[48],"users,":[51],"who":[52],"have":[53],"limited":[54],"insight":[55],"into":[56],"motivations":[58],"behind":[59],"their":[60],"decisions.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65],"perform":[66],"a":[67,114,155],"multi-facet":[68],"analysis":[69],"components":[72],"pre-trained":[74],"and":[75],"fine-tuned":[76],"architectures":[78],"applied":[79,98],"an":[81],"task.":[83],"main":[85],"findings":[86],"resulting":[87],"from":[88],"our":[89],"extensive":[90],"experimental":[91],"evaluation":[92],"(1)":[94],"fine-tuning":[96],"process":[97],"task":[102],"mainly":[103],"modifies":[104],"last":[106],"layers":[107],"components,":[111],"in":[113],"different":[115],"way":[116],"tokens":[118,152],"belonging":[119],"matching":[123],"/":[124],"non-matching":[125],"entities;":[126],"(2)":[127],"special":[129],"structure":[130],"datasets,":[134],"where":[135],"records":[136],"is":[142,153],"recognized":[143],"by":[144,159],"BERT;":[145],"(3)":[146],"pair-wise":[148],"semantic":[149],"similarity":[150],"not":[154],"key":[156],"knowledge":[157],"exploited":[158],"models.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
