{"id":"https://openalex.org/W7170921873","doi":"https://doi.org/10.1007/s10044-026-01744-6","title":"Enhancing blocking for entity matching with pre-trained language model and masked autoencoder","display_name":"Enhancing blocking for entity matching with pre-trained language model and masked autoencoder","publication_year":2026,"publication_date":"2026-07-24","ids":{"openalex":"https://openalex.org/W7170921873","doi":"https://doi.org/10.1007/s10044-026-01744-6"},"language":"en","primary_location":{"id":"doi:10.1007/s10044-026-01744-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10044-026-01744-6","pdf_url":null,"source":{"id":"https://openalex.org/S45497385","display_name":"Pattern Analysis and Applications","issn_l":"1433-7541","issn":["1433-7541","1433-755X"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Analysis and Applications","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/A5143539692","display_name":"Zelin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I114234892","display_name":"Beijing Union University","ror":"https://ror.org/01hg31662","country_code":"CN","type":"education","lineage":["https://openalex.org/I114234892"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zelin Li","raw_affiliation_strings":["Smart City College, Beijing Union University, Beijing, 100101, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Smart City College, Beijing Union University, Beijing, 100101, China","institution_ids":["https://openalex.org/I114234892"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343486","display_name":"Ke Li","orcid":"https://orcid.org/0000-0002-2520-4734"},"institutions":[{"id":"https://openalex.org/I114234892","display_name":"Beijing Union University","ror":"https://ror.org/01hg31662","country_code":"CN","type":"education","lineage":["https://openalex.org/I114234892"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ke Li","raw_affiliation_strings":["Smart City College, Beijing Union University, Beijing, 100101, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Smart City College, Beijing Union University, Beijing, 100101, China","institution_ids":["https://openalex.org/I114234892"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100400207","display_name":"Shuo Wang","orcid":"https://orcid.org/0000-0003-4971-1666"},"institutions":[{"id":"https://openalex.org/I114234892","display_name":"Beijing Union University","ror":"https://ror.org/01hg31662","country_code":"CN","type":"education","lineage":["https://openalex.org/I114234892"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Wang","raw_affiliation_strings":["Smart City College, Beijing Union University, Beijing, 100101, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Smart City College, Beijing Union University, Beijing, 100101, China","institution_ids":["https://openalex.org/I114234892"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100343486"],"corresponding_institution_ids":["https://openalex.org/I114234892"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94747212,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8628000020980835,"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":0.8628000020980835,"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":0.04699999839067459,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.03099999949336052,"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/autoencoder","display_name":"Autoencoder","score":0.803600013256073},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6990000009536743},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4977000057697296},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.49070000648498535},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.46459999680519104},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.44269999861717224},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4307999908924103},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4065999984741211},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.385699987411499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8327999711036682},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.803600013256073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7195000052452087},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6990000009536743},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.526199996471405},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4977000057697296},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.49070000648498535},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.46459999680519104},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4374000132083893},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36480000615119934},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10044-026-01744-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10044-026-01744-6","pdf_url":null,"source":{"id":"https://openalex.org/S45497385","display_name":"Pattern Analysis and Applications","issn_l":"1433-7541","issn":["1433-7541","1433-755X"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Analysis and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6644871234893799,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1992930793","https://openalex.org/W2031250218","https://openalex.org/W2073471108","https://openalex.org/W2111116800","https://openalex.org/W2139490252","https://openalex.org/W2152502401","https://openalex.org/W2798649495","https://openalex.org/W2905135414","https://openalex.org/W2962781182","https://openalex.org/W2992897306","https://openalex.org/W2998702515","https://openalex.org/W3014295153","https://openalex.org/W3014705052","https://openalex.org/W3092962901","https://openalex.org/W3119752913","https://openalex.org/W3146259567","https://openalex.org/W3155638005","https://openalex.org/W3174836606","https://openalex.org/W3197468999","https://openalex.org/W3202439666","https://openalex.org/W4205196528","https://openalex.org/W4281721601","https://openalex.org/W4293238659","https://openalex.org/W4313156423","https://openalex.org/W4317039121","https://openalex.org/W4366729173","https://openalex.org/W4383051975","https://openalex.org/W4386591587","https://openalex.org/W4397029689"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-25T06:00:54.532201","created_date":"2026-07-25T00:00:00"}