{"id":"https://openalex.org/W4403956910","doi":"https://doi.org/10.3389/fcomp.2024.1472512","title":"Combining language models for knowledge extraction from Italian TEI editions","display_name":"Combining language models for knowledge extraction from Italian TEI editions","publication_year":2024,"publication_date":"2024-10-31","ids":{"openalex":"https://openalex.org/W4403956910","doi":"https://doi.org/10.3389/fcomp.2024.1472512"},"language":"en","primary_location":{"id":"doi:10.3389/fcomp.2024.1472512","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fcomp.2024.1472512","pdf_url":"https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2024.1472512/pdf","source":{"id":"https://openalex.org/S4210211086","display_name":"Frontiers in Computer Science","issn_l":"2624-9898","issn":["2624-9898"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2024.1472512/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081729870","display_name":"Cristian Santini","orcid":"https://orcid.org/0000-0001-7363-6737"},"institutions":[{"id":"https://openalex.org/I55133342","display_name":"University of Macerata","ror":"https://ror.org/0001fmy77","country_code":"IT","type":"education","lineage":["https://openalex.org/I55133342"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Cristian Santini","raw_affiliation_strings":["Department of Humanities, University of Macerata, Macerata, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Humanities, University of Macerata, Macerata, Italy","institution_ids":["https://openalex.org/I55133342"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5081729870"],"corresponding_institution_ids":["https://openalex.org/I55133342"],"apc_list":{"value":1150,"currency":"USD","value_usd":1150},"apc_paid":{"value":1150,"currency":"USD","value_usd":1150},"fwci":1.7227,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8726706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"6","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9955000281333923,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9925000071525574,"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/extraction","display_name":"Extraction (chemistry)","score":0.5079739689826965},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49747923016548157},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4892599284648895},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32718759775161743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32650670409202576},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.12466293573379517},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10823079943656921},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.06375300884246826}],"concepts":[{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5079739689826965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49747923016548157},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4892599284648895},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32718759775161743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32650670409202576},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.12466293573379517},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10823079943656921},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.06375300884246826}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3389/fcomp.2024.1472512","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fcomp.2024.1472512","pdf_url":"https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2024.1472512/pdf","source":{"id":"https://openalex.org/S4210211086","display_name":"Frontiers in Computer Science","issn_l":"2624-9898","issn":["2624-9898"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:992731cea02b46f085e6f0537ea4f082","is_oa":true,"landing_page_url":"https://doaj.org/article/992731cea02b46f085e6f0537ea4f082","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Computer Science, Vol 6 (2024)","raw_type":"article"},{"id":"pmh:oai:u-pad.unimc.it:11393/374392","is_oa":true,"landing_page_url":"https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2024.1472512/full","pdf_url":null,"source":{"id":"https://openalex.org/S4377196455","display_name":"U-PAD Unimc - Open Digital Publications (University of Macerata)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I55133342","host_organization_name":"University of Macerata","host_organization_lineage":["https://openalex.org/I55133342"],"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":"doi:10.3389/fcomp.2024.1472512","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fcomp.2024.1472512","pdf_url":"https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2024.1472512/pdf","source":{"id":"https://openalex.org/S4210211086","display_name":"Frontiers in Computer Science","issn_l":"2624-9898","issn":["2624-9898"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403956910.pdf","grobid_xml":"https://content.openalex.org/works/W4403956910.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2032464653","https://openalex.org/W2101282325","https://openalex.org/W2104202709","https://openalex.org/W2109668015","https://openalex.org/W2123442489","https://openalex.org/W2921812231","https://openalex.org/W3010336026","https://openalex.org/W3032553678","https://openalex.org/W3044058576","https://openalex.org/W3101585848","https://openalex.org/W3188575612","https://openalex.org/W3214342214","https://openalex.org/W3217756930","https://openalex.org/W4205317928","https://openalex.org/W4206988054","https://openalex.org/W4288253152","https://openalex.org/W4368618872","https://openalex.org/W4381192993","https://openalex.org/W4385570944","https://openalex.org/W4389520264","https://openalex.org/W4399978597","https://openalex.org/W6852105821","https://openalex.org/W6861428222","https://openalex.org/W6892486341","https://openalex.org/W6892541252","https://openalex.org/W7047403284"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0],"study":[1,177],"investigates":[2],"the":[3,62,86,96,161,187,213],"integration":[4],"of":[5,64,141,149,189],"language":[6,51,83,102],"models":[7,52,66,185],"for":[8,35],"knowledge":[9,29],"extraction":[10,57],"(KE)":[11],"from":[12,32,85,145,192],"Italian":[13,68],"TEI/XML":[14,143],"encoded":[15],"texts,":[16],"focusing":[17],"on":[18],"Giacomo":[19],"Leopardi's":[20,150,207],"works.":[21],"The":[22,43,71,119,136,155,195],"objective":[23],"is":[24,113],"to":[25,40,60,80,104,115,206,217],"create":[26],"structured,":[27],"machine-readable":[28],"graphs":[30],"(KGs)":[31],"unstructured":[33],"texts":[34],"better":[36],"exploration":[37],"and":[38,133,173,210,221],"linkage":[39],"external":[41],"resources.":[42],"research":[44,137],"introduces":[45],"a":[46,74,139,146],"methodology":[47],"that":[48,77,164,179],"combines":[49],"large":[50],"(LLMs)":[53],"with":[54,67,127,167,182],"traditional":[55,183],"relation":[56],"(RE)":[58],"algorithms":[59],"overcome":[61],"limitations":[63],"current":[65],"literary":[69,208],"documents.":[70],"process":[72],"adopts":[73],"multilingual":[75],"LLM,":[76],"is,":[78,165],"ChatGPT,":[79],"extract":[81],"natural":[82,101],"triples":[84,126],"text.":[87],"These":[88],"are":[89],"then":[90],"converted":[91],"into":[92],"RDF/XML":[93],"format":[94],"using":[95,111],"REBEL":[97],"model,":[98,163],"which":[99],"maps":[100],"relations":[103],"Wikidata":[105],"properties.":[106],"A":[107],"similarity-based":[108],"filtering":[109],"mechanism":[110],"SBERT":[112],"applied":[114],"keep":[116],"semantic":[117,171],"consistency.":[118,174],"final":[120],"RDF":[121],"graph":[122],"integrates":[123],"these":[124],"filtered":[125],"document":[128],"metadata,":[129],"utilizing":[130],"established":[131],"ontologies":[132],"controlled":[134],"vocabularies.":[135],"uses":[138],"dataset":[140],"41":[142],"files":[144],"semi-diplomatic":[147],"edition":[148],"letters":[151],"as":[152],"case":[153],"study.":[154],"proposed":[156],"KE":[157],"pipeline":[158],"significantly":[159],"outperformed":[160],"baseline":[162],"mREBEL,":[166],"remarkable":[168],"improvements":[169],"in":[170],"accuracy":[172],"An":[175],"ablation":[176],"demonstrated":[178],"combining":[180],"LLMs":[181],"RE":[184],"enhances":[186],"quality":[188],"KGs":[190],"extracted":[191,214],"complex":[193],"texts.":[194],"resulting":[196],"KG":[197],"had":[198],"fewer,":[199],"but":[200],"semantically":[201],"richer,":[202],"relations,":[203],"predominantly":[204],"related":[205],"activities":[209],"health,":[211],"highlighting":[212],"knowledge's":[215],"relevance":[216],"understanding":[218],"his":[219],"life":[220],"work.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}