{"id":"https://openalex.org/W4386919110","doi":"https://doi.org/10.1007/978-3-031-43849-3_18","title":"A Graph Neural Network Approach for\u00a0Evaluating Correctness of\u00a0Groups of\u00a0Duplicates","display_name":"A Graph Neural Network Approach for\u00a0Evaluating Correctness of\u00a0Groups of\u00a0Duplicates","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386919110","doi":"https://doi.org/10.1007/978-3-031-43849-3_18"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-43849-3_18","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-43849-3_18","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-43849-3_18.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-43849-3_18.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043605025","display_name":"Michele De Bonis","orcid":"https://orcid.org/0000-0003-2347-6012"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Michele De Bonis","raw_affiliation_strings":["Istituto di Scienza e Tecnologie dell\u2019Informazione \u201cA. Faedo\u201d - ISTI (CNR), Pisa, Italy","Istituto di Scienza e Tecnologie dell'Informazione \"A. Faedo\" - ISTI (CNR), Pisa, Italy"],"raw_orcid":"https://orcid.org/0000-0003-2347-6012","affiliations":[{"raw_affiliation_string":"Istituto di Scienza e Tecnologie dell\u2019Informazione \u201cA. Faedo\u201d - ISTI (CNR), Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]},{"raw_affiliation_string":"Istituto di Scienza e Tecnologie dell'Informazione \"A. Faedo\" - ISTI (CNR), Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007288613","display_name":"Filippo Minutella","orcid":null},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Filippo Minutella","raw_affiliation_strings":["TIM S.p.A., Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TIM S.p.A., Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047189288","display_name":"Fabrizio Falchi","orcid":"https://orcid.org/0000-0001-6258-5313"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabrizio Falchi","raw_affiliation_strings":["Istituto di Scienza e Tecnologie dell\u2019Informazione \u201cA. Faedo\u201d - ISTI (CNR), Pisa, Italy","Istituto di Scienza e Tecnologie dell'Informazione \"A. Faedo\" - ISTI (CNR), Pisa, Italy"],"raw_orcid":"https://orcid.org/0000-0001-6258-5313","affiliations":[{"raw_affiliation_string":"Istituto di Scienza e Tecnologie dell\u2019Informazione \u201cA. Faedo\u201d - ISTI (CNR), Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]},{"raw_affiliation_string":"Istituto di Scienza e Tecnologie dell'Informazione \"A. Faedo\" - ISTI (CNR), Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087882533","display_name":"Paolo Manghi","orcid":"https://orcid.org/0000-0001-7291-3210"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Manghi","raw_affiliation_strings":["Istituto di Scienza e Tecnologie dell\u2019Informazione \u201cA. Faedo\u201d - ISTI (CNR), Pisa, Italy","OpenAIRE AMKE, Pisa, Italy"],"raw_orcid":"https://orcid.org/0000-0001-7291-3210","affiliations":[{"raw_affiliation_string":"Istituto di Scienza e Tecnologie dell\u2019Informazione \u201cA. Faedo\u201d - ISTI (CNR), Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]},{"raw_affiliation_string":"OpenAIRE AMKE, Pisa, Italy","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043605025"],"corresponding_institution_ids":["https://openalex.org/I122991210"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.9969,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80881764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"207","last_page":"219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9962999820709229,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8623685836791992},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7319211363792419},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5130406618118286},{"id":"https://openalex.org/keywords/transitive-closure","display_name":"Transitive closure","score":0.5051224827766418},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47595450282096863},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4324277937412262},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4323720932006836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3879980444908142},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38337862491607666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1572083830833435},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10153031349182129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8623685836791992},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7319211363792419},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5130406618118286},{"id":"https://openalex.org/C128896722","wikidata":"https://www.wikidata.org/wiki/Q1501387","display_name":"Transitive closure","level":2,"score":0.5051224827766418},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47595450282096863},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4324277937412262},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4323720932006836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3879980444908142},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38337862491607666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1572083830833435},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10153031349182129},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-031-43849-3_18","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-43849-3_18","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-43849-3_18.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:dnet:people______::352e748420e6ed1331c8bf6476966c65","is_oa":true,"landing_page_url":"https://openportal.isti.cnr.it/doc?id=people______::352e748420e6ed1331c8bf6476966c65","pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"TPDL 2023 - 27th International Conference on Theory and Practice of Digital Libraries, pp. 207\u2013219, Zadar, Croatia, 26-29/09/2023","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-43849-3_18","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-43849-3_18","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-43849-3_18.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G265104915","display_name":null,"funder_award_id":"EC H2020","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G5644912080","display_name":null,"funder_award_id":"101017452","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386919110.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W92903312","https://openalex.org/W1982195966","https://openalex.org/W1986017822","https://openalex.org/W1986313415","https://openalex.org/W2064675550","https://openalex.org/W2985331920","https://openalex.org/W4247914182","https://openalex.org/W4294712703","https://openalex.org/W4393729356","https://openalex.org/W6601955380","https://openalex.org/W6702248584","https://openalex.org/W6762248821","https://openalex.org/W6802415111"],"related_works":["https://openalex.org/W2359423766","https://openalex.org/W1600485007","https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W2364216866","https://openalex.org/W4247536566","https://openalex.org/W2362009423","https://openalex.org/W4241418540","https://openalex.org/W2018477250","https://openalex.org/W3119814709"],"abstract_inverted_index":{"Abstract":[0],"Unlabeled":[1],"entity":[2,24],"deduplication":[3],"is":[4,70,104,132],"a":[5,64,107,143,148],"relevant":[6],"task":[7],"already":[8],"studied":[9],"in":[10,134],"the":[11,21,38,81,93,115,129,135,151],"recent":[12],"literature.":[13],"Most":[14],"methods":[15,55],"can":[16,88],"be":[17,89],"traced":[18],"back":[19],"to":[20,32,41,51,91,142],"following":[22],"workflow:":[23],"blocking":[25],"phase,":[26],"in-block":[27],"pairwise":[28],"comparisons":[29],"between":[30],"entities":[31,50],"draw":[33],"similarity":[34],"relations,":[35],"closure":[36],"of":[37,44,83,85,99,117,128,137,150],"resulting":[39],"meshes":[40],"create":[42],"groups":[43],"duplicate":[45],"entities,":[46],"and":[47,113,120],"merging":[48],"group":[49],"remove":[52],"disambiguation.":[53],"Such":[54],"are":[56],"effective":[57],"but":[58],"still":[59],"not":[60],"good":[61],"enough":[62],"whenever":[63],"very":[65],"low":[66],"false":[67],"positive":[68],"rate":[69],"required.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75],"present":[76],"an":[77],"approach":[78,103,131],"for":[79],"evaluating":[80],"correctness":[82],"\u201cgroups":[84],"duplicates\u201d,":[86],"which":[87],"used":[90],"measure":[92],"group\u2019s":[94],"accuracy":[95,127],"hence":[96],"its":[97],"likelihood":[98],"false-positiveness.":[100],"Our":[101],"novel":[102],"based":[105],"on":[106],"Graph":[108,118,153],"Neural":[109],"Network":[110],"that":[111,154],"exploits":[112],"combines":[114],"concept":[116],"Attention":[119],"Long":[121],"Short":[122],"Term":[123],"Memory":[124],"(LSTM).":[125],"The":[126],"proposed":[130],"verified":[133],"context":[136],"Author":[138],"Name":[139],"Disambiguation":[140],"applied":[141],"curated":[144],"dataset":[145],"obtained":[146],"as":[147],"subset":[149],"OpenAIRE":[152],"includes":[155],"PubMed":[156],"publications":[157],"with":[158],"at":[159],"least":[160],"one":[161],"ORCID":[162],"identifier.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}