{"id":"https://openalex.org/W4383051975","doi":"https://doi.org/10.14778/3598581.3598594","title":"Pre-Trained Embeddings for Entity Resolution: An Experimental Analysis","display_name":"Pre-Trained Embeddings for Entity Resolution: An Experimental Analysis","publication_year":2023,"publication_date":"2023-05-01","ids":{"openalex":"https://openalex.org/W4383051975","doi":"https://doi.org/10.14778/3598581.3598594"},"language":"en","primary_location":{"id":"doi:10.14778/3598581.3598594","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3598581.3598594","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://zenodo.org/record/8083349","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050605929","display_name":"Alexandros Zeakis","orcid":"https://orcid.org/0000-0001-5336-8157"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Alexandros Zeakis","raw_affiliation_strings":["National and Kapodistrian University of Athens & Athena Research Center, Athens, Greece","National and Kapodistrian University of Athens &","Athena Research Center Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National and Kapodistrian University of Athens & Athena Research Center, Athens, Greece","institution_ids":["https://openalex.org/I200777214"]},{"raw_affiliation_string":"National and Kapodistrian University of Athens &","institution_ids":["https://openalex.org/I200777214"]},{"raw_affiliation_string":"Athena Research Center Athens, Greece","institution_ids":["https://openalex.org/I4210156054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056976720","display_name":"George Papadakis","orcid":"https://orcid.org/0000-0002-7298-9431"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"George Papadakis","raw_affiliation_strings":["National and Kapodistrian University of Athens, Athens, Greece","National and Kapodistrian University of Athens &","Athena Research Center Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National and Kapodistrian University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I200777214"]},{"raw_affiliation_string":"National and Kapodistrian University of Athens &","institution_ids":["https://openalex.org/I200777214"]},{"raw_affiliation_string":"Athena Research Center Athens, Greece","institution_ids":["https://openalex.org/I4210156054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087768208","display_name":"Dimitrios Skoutas","orcid":"https://orcid.org/0000-0002-6118-5227"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitrios Skoutas","raw_affiliation_strings":["Athena Research Center, Athens, Greece","National and Kapodistrian University of Athens &","National and Kapodistrian University of Athens Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Athena Research Center, Athens, Greece","institution_ids":["https://openalex.org/I4210156054"]},{"raw_affiliation_string":"National and Kapodistrian University of Athens &","institution_ids":["https://openalex.org/I200777214"]},{"raw_affiliation_string":"National and Kapodistrian University of Athens Athens, Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075117735","display_name":"Manolis Koubarakis","orcid":"https://orcid.org/0000-0002-1954-8338"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Manolis Koubarakis","raw_affiliation_strings":["National and Kapodistrian University of Athens, Athens, Greece","National and Kapodistrian University of Athens &","Athena Research Center Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National and Kapodistrian University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I200777214"]},{"raw_affiliation_string":"National and Kapodistrian University of Athens &","institution_ids":["https://openalex.org/I200777214"]},{"raw_affiliation_string":"Athena Research Center Athens, Greece","institution_ids":["https://openalex.org/I4210156054"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.2404,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.98325679,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"16","issue":"9","first_page":"2225","last_page":"2238"},"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":0.9959999918937683,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9693999886512756,"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":0.8261462450027466},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.786979079246521},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7008528113365173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6535252332687378},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6250923871994019},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.5272159576416016},{"id":"https://openalex.org/keywords/strengths-and-weaknesses","display_name":"Strengths and weaknesses","score":0.5188832879066467},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.5138523578643799},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.505828857421875},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5023746490478516},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4893438220024109},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4834955036640167},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4741646349430084},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.462058424949646},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07443153858184814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8261462450027466},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.786979079246521},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7008528113365173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6535252332687378},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6250923871994019},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.5272159576416016},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.5188832879066467},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.5138523578643799},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.505828857421875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5023746490478516},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4893438220024109},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4834955036640167},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4741646349430084},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.462058424949646},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07443153858184814},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","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},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3598581.3598594","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3598581.3598594","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:zenodo.org:8083349","is_oa":true,"landing_page_url":"https://zenodo.org/record/8083349","pdf_url":"https://zenodo.org/record/8083349","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Proceedings of the VLDB Endowment 16(9) 2225--2238","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:8083349","is_oa":true,"landing_page_url":"https://zenodo.org/record/8083349","pdf_url":"https://zenodo.org/record/8083349","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Proceedings of the VLDB Endowment 16(9) 2225--2238","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7300000190734863}],"awards":[{"id":"https://openalex.org/G4524914691","display_name":null,"funder_award_id":"HFRI-FM17-2351","funder_id":"https://openalex.org/F4320327859","funder_display_name":"Hellenic Foundation for Research and Innovation"},{"id":"https://openalex.org/G5741899482","display_name":null,"funder_award_id":"101070122","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320327859","display_name":"Hellenic Foundation for Research and Innovation","ror":null},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4383051975.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1981590391","https://openalex.org/W1992930793","https://openalex.org/W1997927541","https://openalex.org/W2011940398","https://openalex.org/W2031250218","https://openalex.org/W2041439319","https://openalex.org/W2210065635","https://openalex.org/W2250539671","https://openalex.org/W2399361902","https://openalex.org/W2493916176","https://openalex.org/W2798649495","https://openalex.org/W2951147191","https://openalex.org/W2963265099","https://openalex.org/W2963469388","https://openalex.org/W2970641574","https://openalex.org/W2981852735","https://openalex.org/W2985009327","https://openalex.org/W2986591322","https://openalex.org/W3008374555","https://openalex.org/W3011807731","https://openalex.org/W3012733951","https://openalex.org/W3014295153","https://openalex.org/W3014705052","https://openalex.org/W3016473712","https://openalex.org/W3029701880","https://openalex.org/W3034997167","https://openalex.org/W3098205952","https://openalex.org/W3106020963","https://openalex.org/W3123375411","https://openalex.org/W3138971549","https://openalex.org/W3174836606","https://openalex.org/W3176831585","https://openalex.org/W3197468999","https://openalex.org/W4213009331","https://openalex.org/W4249682906","https://openalex.org/W4283314192","https://openalex.org/W4288089799","https://openalex.org/W4298196171","https://openalex.org/W4312903631","https://openalex.org/W4367060427","https://openalex.org/W4393781750"],"related_works":["https://openalex.org/W2762467749","https://openalex.org/W2161584192","https://openalex.org/W2374048355","https://openalex.org/W2359910081","https://openalex.org/W2381929598","https://openalex.org/W2383797864","https://openalex.org/W3024308452","https://openalex.org/W4295769391","https://openalex.org/W2364351544","https://openalex.org/W2100785378"],"abstract_inverted_index":{"Many":[0],"recent":[1],"works":[2],"on":[3],"Entity":[4],"Resolution":[5],"(ER)":[6],"leverage":[7],"Deep":[8],"Learning":[9],"techniques":[10],"involving":[11],"language":[12,73,143],"models":[13,74],"to":[14,20,149],"improve":[15],"effectiveness.":[16],"This":[17],"is":[18,51],"applied":[19],"both":[21,124],"main":[22,142],"steps":[23],"of":[24,45,55,70,140],"ER,":[25],"i.e.,":[26],"blocking":[27,99,114],"and":[28,43,58,106,126,138,147],"matching.":[29,128],"Several":[30],"pre-trained":[31],"embeddings":[32,93],"have":[33],"been":[34],"tested,":[35],"with":[36,109,119],"the":[37,46,110,136,141,151],"most":[38,152],"popular":[39,72],"ones":[40,154],"being":[41],"fastText":[42],"variants":[44],"BERT":[47],"model.":[48],"However,":[49],"there":[50],"no":[52],"detailed":[53,103],"analysis":[54,69],"their":[56,83,98,120],"pros":[57],"cons.":[59],"To":[60],"cover":[61],"this":[62],"gap,":[63],"we":[64,81,96,117],"perform":[65],"a":[66,102],"thorough":[67],"experimental":[68,130],"12":[71],"over":[75],"17":[76],"established":[77],"benchmark":[78],"datasets.":[79],"First,":[80],"assess":[82],"vectorization":[84],"overhead":[85],"for":[86,123],"converting":[87],"all":[88],"input":[89],"entities":[90],"into":[91,135],"dense":[92],"vectors.":[94],"Second,":[95],"investigate":[97],"performance,":[100],"performing":[101],"scalability":[104],"analysis,":[105],"comparing":[107],"them":[108],"state-of-the-art":[111],"deep":[112],"learning-based":[113],"method.":[115],"Third,":[116],"conclude":[118],"relative":[121],"performance":[122],"supervised":[125],"unsupervised":[127],"Our":[129],"results":[131],"provide":[132],"novel":[133],"insights":[134],"strengths":[137],"weaknesses":[139],"models,":[144],"facilitating":[145],"researchers":[146],"practitioners":[148],"select":[150],"suitable":[153],"in":[155],"practice.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}