{"id":"https://openalex.org/W4413141549","doi":"https://doi.org/10.1007/s00521-025-11449-2","title":"A novel NLP-driven approach for enriching artefact descriptions, provenance, and entities in cultural heritage","display_name":"A novel NLP-driven approach for enriching artefact descriptions, provenance, and entities in cultural heritage","publication_year":2025,"publication_date":"2025-08-13","ids":{"openalex":"https://openalex.org/W4413141549","doi":"https://doi.org/10.1007/s00521-025-11449-2"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-025-11449-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11449-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11449-2.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11449-2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033547474","display_name":"Sara Ferro","orcid":"https://orcid.org/0000-0001-9937-7112"},"institutions":[{"id":"https://openalex.org/I4210133865","display_name":"Center for Cultural Heritage Technology","ror":"https://ror.org/03mk1jb23","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210133865"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Sara Ferro","raw_affiliation_strings":["Centre for Cultural Heritage Technology (CCHT), Fondazione Istituto Italiano di Tecnologia, Via Adriano Olivetti 1, 31056, Treviso, Italy"],"affiliations":[{"raw_affiliation_string":"Centre for Cultural Heritage Technology (CCHT), Fondazione Istituto Italiano di Tecnologia, Via Adriano Olivetti 1, 31056, Treviso, Italy","institution_ids":["https://openalex.org/I4210133865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027207716","display_name":"Riccardo Giovanelli","orcid":"https://orcid.org/0000-0001-8884-8492"},"institutions":[{"id":"https://openalex.org/I4210133865","display_name":"Center for Cultural Heritage Technology","ror":"https://ror.org/03mk1jb23","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210133865"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Riccardo Giovanelli","raw_affiliation_strings":["Centre for Cultural Heritage Technology (CCHT), Fondazione Istituto Italiano di Tecnologia, Via Adriano Olivetti 1, 31056, Treviso, Italy"],"affiliations":[{"raw_affiliation_string":"Centre for Cultural Heritage Technology (CCHT), Fondazione Istituto Italiano di Tecnologia, Via Adriano Olivetti 1, 31056, Treviso, Italy","institution_ids":["https://openalex.org/I4210133865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091177242","display_name":"Madison Leeson","orcid":"https://orcid.org/0000-0001-8282-836X"},"institutions":[{"id":"https://openalex.org/I4210133865","display_name":"Center for Cultural Heritage Technology","ror":"https://ror.org/03mk1jb23","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210133865"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Madison Leeson","raw_affiliation_strings":["Centre for Cultural Heritage Technology (CCHT), Fondazione Istituto Italiano di Tecnologia, Via Adriano Olivetti 1, 31056, Treviso, Italy"],"affiliations":[{"raw_affiliation_string":"Centre for Cultural Heritage Technology (CCHT), Fondazione Istituto Italiano di Tecnologia, Via Adriano Olivetti 1, 31056, Treviso, Italy","institution_ids":["https://openalex.org/I4210133865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092618062","display_name":"Michela De Bernardin","orcid":"https://orcid.org/0000-0003-1687-459X"},"institutions":[{"id":"https://openalex.org/I4210133865","display_name":"Center for Cultural Heritage Technology","ror":"https://ror.org/03mk1jb23","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210133865"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michela De Bernardin","raw_affiliation_strings":["Centre for Cultural Heritage Technology (CCHT), Fondazione Istituto Italiano di Tecnologia, Via Adriano Olivetti 1, 31056, Treviso, Italy"],"affiliations":[{"raw_affiliation_string":"Centre for Cultural Heritage Technology (CCHT), Fondazione Istituto Italiano di Tecnologia, Via Adriano Olivetti 1, 31056, Treviso, Italy","institution_ids":["https://openalex.org/I4210133865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025092398","display_name":"Arianna Traviglia","orcid":"https://orcid.org/0000-0002-4508-1540"},"institutions":[{"id":"https://openalex.org/I4210133865","display_name":"Center for Cultural Heritage Technology","ror":"https://ror.org/03mk1jb23","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210133865"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Arianna Traviglia","raw_affiliation_strings":["Centre for Cultural Heritage Technology (CCHT), Fondazione Istituto Italiano di Tecnologia, Via Adriano Olivetti 1, 31056, Treviso, Italy"],"affiliations":[{"raw_affiliation_string":"Centre for Cultural Heritage Technology (CCHT), Fondazione Istituto Italiano di Tecnologia, Via Adriano Olivetti 1, 31056, Treviso, Italy","institution_ids":["https://openalex.org/I4210133865"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5033547474"],"corresponding_institution_ids":["https://openalex.org/I4210133865"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":5.2159,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.9579339,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"37","issue":"25","first_page":"21275","last_page":"21296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9818000197410583,"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/T12364","display_name":"Archaeological Research and Protection","score":0.9797000288963318,"subfield":{"id":"https://openalex.org/subfields/1912","display_name":"Space and Planetary Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.7070541977882385},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6442045569419861},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6134154796600342},{"id":"https://openalex.org/keywords/cultural-heritage","display_name":"Cultural heritage","score":0.5777787566184998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5608925819396973},{"id":"https://openalex.org/keywords/provenance","display_name":"Provenance","score":0.5534046292304993},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21896034479141235},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.16313990950584412},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.13003608584403992},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.12246078252792358},{"id":"https://openalex.org/keywords/paleontology","display_name":"Paleontology","score":0.10691535472869873}],"concepts":[{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.7070541977882385},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6442045569419861},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6134154796600342},{"id":"https://openalex.org/C60671577","wikidata":"https://www.wikidata.org/wiki/Q210272","display_name":"Cultural heritage","level":2,"score":0.5777787566184998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5608925819396973},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.5534046292304993},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21896034479141235},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.16313990950584412},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.13003608584403992},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.12246078252792358},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.10691535472869873}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-025-11449-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11449-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11449-2.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00521-025-11449-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11449-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11449-2.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3514550006","display_name":null,"funder_award_id":"Centre","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5289481581","display_name":null,"funder_award_id":"101073932","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8391788003","display_name":null,"funder_award_id":"101073932","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320325847","display_name":"Istituto Italiano di Tecnologia","ror":"https://ror.org/042t93s57"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413141549.pdf","grobid_xml":"https://content.openalex.org/works/W4413141549.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1582487692","https://openalex.org/W2109668015","https://openalex.org/W2147800946","https://openalex.org/W2215206286","https://openalex.org/W2583580911","https://openalex.org/W2890454345","https://openalex.org/W2982546989","https://openalex.org/W3010336026","https://openalex.org/W3011594683","https://openalex.org/W3102436196","https://openalex.org/W3155329622","https://openalex.org/W4241101798","https://openalex.org/W4390886637","https://openalex.org/W4404337998","https://openalex.org/W4404752285","https://openalex.org/W4411072335","https://openalex.org/W6892471735"],"related_works":["https://openalex.org/W2354627941","https://openalex.org/W2347483153","https://openalex.org/W2353379336","https://openalex.org/W2379683085","https://openalex.org/W2363868702","https://openalex.org/W2374448931","https://openalex.org/W2376723740","https://openalex.org/W2370535391","https://openalex.org/W2370679613","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Despite":[0],"the":[1,24,51,78,98,101,162,166,180,188,211],"availability":[2],"of":[3,20,26,53,100,144,213],"numerous":[4],"open":[5],"datasets":[6,55,69,95,151],"on":[7,14,93,117,138,147,170,191],"cultural":[8,126,222],"heritage,":[9],"limited":[10],"research":[11],"has":[12],"focussed":[13],"structuring":[15],"and":[16,38,62,80,109,130],"normalising":[17],"this":[18,72],"type":[19],"data,":[21],"particularly":[22],"through":[23],"extraction":[25,216],"entities":[27],"from":[28,119,165],"unstructured":[29],"texts.":[30],"This":[31,43,173,208],"step":[32],"is":[33],"crucial":[34],"for":[35,56,83,107,221],"enriching,":[36],"analysing,":[37],"understanding":[39],"these":[40,148],"complex":[41],"datasets.":[42],"study":[44],"presents":[45],"a":[46,131],"procedure":[47],"designed":[48],"to":[49,179,198,217],"streamline":[50],"creation":[52],"domain-specific":[54],"training":[57,143],"natural":[58],"language":[59],"processing":[60],"models":[61,92,146,155],"evaluates":[63],"their":[64,158],"performance":[65],"across":[66],"three":[67,94],"distinct":[68],"generated":[70],"using":[71],"procedure.":[73],"A":[74],"zero-shot":[75],"learning":[76],"model,":[77],"Generalist":[79],"Lightweight":[81],"Model":[82],"Named":[84],"Entity":[85],"Recognition,":[86],"was":[87],"assessed":[88],"alongside":[89],"pre-trained":[90],"spaCy":[91,145],"created":[96],"in":[97,128,183],"framework":[99],"European":[102],"Union-funded":[103],"Research":[104],"Intelligence":[105],"Technology":[106],"Heritage":[108],"Market":[110],"Security":[111],"project:":[112],"one":[113],"containing":[114,201],"provenance":[115,171,184],"information":[116,193],"artefacts":[118],"North":[120],"American":[121],"museums,":[122],"another":[123],"detailing":[124],"stolen":[125],"goods":[127],"Romania,":[129],"third":[132],"with":[133,161],"structured":[134],"yet":[135],"unclassified":[136],"data":[137,203],"WWII-looted":[139],"Polish":[140],"art.":[141],"Further":[142],"newly":[149],"defined":[150],"revealed":[152],"that":[153,204],"fine-tuned":[154,169,190],"significantly":[156],"outperform":[157],"non-fine-tuned":[159],"counterparts,":[160],"best":[163],"results":[164],"Transformer":[167],"model":[168,189,206],"data.":[172],"success":[174],"can":[175],"be":[176],"largely":[177],"attributed":[178],"standardised":[181],"conventions":[182],"research.":[185],"In":[186],"contrast,":[187],"descriptive":[192],"performed":[194],"poorly,":[195],"likely":[196],"due":[197],"extensive":[199],"descriptions":[200],"non-essential":[202],"increased":[205],"uncertainty.":[207],"work":[209],"highlights":[210],"potential":[212],"automating":[214],"entity":[215],"build":[218],"knowledge":[219],"graphs":[220],"object":[223],"databases,":[224],"enabling":[225],"advanced":[226],"analytical":[227],"approaches":[228],"such":[229],"as":[230],"Network":[231],"Analysis.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}