{"id":"https://openalex.org/W7204189053","doi":"https://doi.org/10.34934/dvn/hna7qo","title":"Replication Data for: From nineteenth-century letters to entities: \"a NER pipeline for French correspondence and its methodological lessons\" - Article for Digital Humanities Benelux Journal","display_name":"Replication Data for: From nineteenth-century letters to entities: \"a NER pipeline for French correspondence and its methodological lessons\" - Article for Digital Humanities Benelux Journal","publication_year":2026,"publication_date":"2026-06-22","ids":{"openalex":"https://openalex.org/W7204189053","doi":"https://doi.org/10.34934/dvn/hna7qo"},"language":"en","primary_location":{"id":"doi:10.34934/dvn/hna7qo","doi":"https://doi.org/10.34934/dvn/hna7qo","is_oa":true,"landing_page_url":"https://doi.org/10.34934/dvn/hna7qo","pdf_url":null,"source":{"id":"https://openalex.org/S7407052680","display_name":"SODHA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210140745","host_organization_name":"State Archives of Belgium","host_organization_lineage":["https://openalex.org/I4210140745"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.34934/dvn/hna7qo","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014250784","display_name":"Zuzana \u010cern\u00e1kov\u00e1","orcid":"https://orcid.org/0000-0002-6417-550X","observed_orcids":["https://orcid.org/0000-0002-6417-550X"]},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Zuzana \u010cern\u00e1kov\u00e1","raw_affiliation_strings":["(Department of History, Ghent University; Digital Research Lab, KBR)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Department of History, Ghent University; Digital Research Lab, KBR)","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040889762","display_name":"Fien Messens","orcid":"https://orcid.org/0000-0003-3150-5469","observed_orcids":["https://orcid.org/0000-0003-3150-5469"]},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Fien Messens","raw_affiliation_strings":["(Department of History, Ghent University; KBR)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Department of History, Ghent University; KBR)","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091985592","display_name":"Tess Dejaeghere","orcid":"https://orcid.org/0000-0002-8472-4457","observed_orcids":["https://orcid.org/0000-0002-8472-4457"]},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I4405284184","display_name":"Ghent Centre for Digital Humanities","ror":"https://ror.org/033xkh119","country_code":"BE","type":"facility","lineage":["https://openalex.org/I32597200","https://openalex.org/I4405284184"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tess Dejaeghere","raw_affiliation_strings":["(Ghent Centre for Digital Humanities; Language Translation and Technology Team, Ghent University)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Ghent Centre for Digital Humanities; Language Translation and Technology Team, Ghent University)","institution_ids":["https://openalex.org/I32597200","https://openalex.org/I4405284184"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050656741","display_name":"Julie M. Birkholz","orcid":"https://orcid.org/0000-0003-1193-0847","observed_orcids":["https://orcid.org/0000-0003-1193-0847"]},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I4405284184","display_name":"Ghent Centre for Digital Humanities","ror":"https://ror.org/033xkh119","country_code":"BE","type":"facility","lineage":["https://openalex.org/I32597200","https://openalex.org/I4405284184"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Julie M. Birkholz","raw_affiliation_strings":["(Ghent Centre for Digital Humanities; Department of History, Ghent University; Digital Research Lab, KBR)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Ghent Centre for Digital Humanities; Department of History, Ghent University; Digital Research Lab, KBR)","institution_ids":["https://openalex.org/I32597200","https://openalex.org/I4405284184"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5214999914169312,"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/T10028","display_name":"Topic Modeling","score":0.5214999914169312,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.461899995803833,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.007499999832361937,"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/named-entity-recognition","display_name":"named entity recognition","score":0.9990000128746033},{"id":"https://openalex.org/keywords/nineteenth-century-letters","display_name":"19th-century correspondence","score":0.8080000281333923},{"id":"https://openalex.org/keywords/french-correspondence","display_name":"French correspondence","score":0.9779999852180481},{"id":"https://openalex.org/keywords/spacy","display_name":"spaCy","score":0.8859999775886536},{"id":"https://openalex.org/keywords/camembert","display_name":"Camembert","score":0.8659999966621399},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.6470000147819519},{"id":"https://openalex.org/keywords/gold-standard-annotation","display_name":"gold standard annotation","score":0.6629999876022339},{"id":"https://openalex.org/keywords/historical-text-processing","display_name":"historical text processing","score":0.4650000035762787},{"id":"https://openalex.org/keywords/error-analysis","display_name":"error analysis","score":0.328000009059906}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7906000018119812},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7502999901771545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6775000095367432},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.61080002784729},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5242000222206116},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4747999906539917},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4717000126838684},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4571000039577484},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4564000070095062},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3190000057220459},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.31679999828338623},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2574000060558319},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.34934/dvn/hna7qo","doi":"https://doi.org/10.34934/dvn/hna7qo","is_oa":true,"landing_page_url":"https://doi.org/10.34934/dvn/hna7qo","pdf_url":null,"source":{"id":"https://openalex.org/S7407052680","display_name":"SODHA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210140745","host_organization_name":"State Archives of Belgium","host_organization_lineage":["https://openalex.org/I4210140745"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.34934/dvn/hna7qo","doi":"https://doi.org/10.34934/dvn/hna7qo","is_oa":true,"landing_page_url":"https://doi.org/10.34934/dvn/hna7qo","pdf_url":null,"source":{"id":"https://openalex.org/S7407052680","display_name":"SODHA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210140745","host_organization_name":"State Archives of Belgium","host_organization_lineage":["https://openalex.org/I4210140745"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6912819148","https://openalex.org/W4283361265","https://openalex.org/W4392012561","https://openalex.org/W7083014359","https://openalex.org/W4281661237","https://openalex.org/W6911968449","https://openalex.org/W6891710859","https://openalex.org/W4414565878","https://openalex.org/W947855104","https://openalex.org/W4301672185"],"abstract_inverted_index":{"This":[0],"dataset":[1,62],"accompanies":[2],"the":[3,24,51,64,69,78,106,111,116,124,128,132,140,144,162,165,188,201,205],"article":[4],"From":[5],"nineteenth-century":[6,47],"letters":[7],"to":[8,37,77,199],"entities:":[9],"A":[10],"Named":[11,41],"Entity":[12,42],"Recognition":[13,43],"pipeline":[14],"for":[15,46],"French":[16,48],"correspondence":[17,49],"and":[18,33,39,88,94,115,119,135,151,157,180,192,195],"its":[19],"methodological":[20],"lessons.":[21],"It":[22],"contains":[23,105,139,161],"input":[25],"data,":[26],"preprocessing":[27],"scripts,":[28],"analysis":[29],"notebooks,":[30],"evaluation":[31,79,136,141],"outputs,":[32],"experimental":[34,66],"results":[35,142],"used":[36,122],"develop":[38],"evaluate":[40],"(NER)":[44],"workflows":[45],"from":[50,68],"Fran\u00e7ois-Joseph":[52],"Navez":[53],"corpus":[54,76],"(KBR":[55],"\u2013":[56],"Royal":[57],"Library":[58],"of":[59,71,80,143,164],"Belgium).":[60],"The":[61,97],"documents":[63],"complete":[65,189],"workflow,":[67],"construction":[70],"a":[72,84],"manually":[73],"annotated":[74],"gold-standard":[75,113],"off-the-shelf":[81],"spaCy":[82,86,145],"models,":[83],"custom-trained":[85],"model,":[87],"transformer-based":[89,166],"models":[90],"(CamemBERT,":[91],"CamemBERTav2,":[92],"D'AlemBERT":[93],"Europeana":[95],"BERT).":[96],"repository":[98],"is":[99],"organised":[100],"into":[101],"four":[102],"directories.":[103],"Input":[104],"Label":[107],"Studio":[108],"annotation":[109],"exports,":[110],"preprocessed":[112],"corpus,":[114],"training,":[117],"development":[118],"test":[120],"splits":[121],"throughout":[123],"experiments.":[125],"Notebooks":[126],"provides":[127],"Jupyter":[129],"notebooks":[130],"implementing":[131],"preprocessing,":[133],"training":[134],"workflows.":[137],"Output":[138],"experiments,":[146,167],"including":[147,168],"model":[148],"predictions,":[149],"overall":[150],"per-entity":[152],"performance":[153],"metrics,":[154],"mismatch":[155],"analyses":[156,202],"summary":[158],"tables.":[159],"Results_transformers":[160],"outputs":[163,197],"hyperparameter":[169],"optimisation,":[170],"cross-validation":[171],"results,":[172],"learning":[173],"curves,":[174],"statistical":[175],"significance":[176],"tests,":[177],"prediction":[178],"files":[179,186],"qualitative":[181],"error":[182],"analyses.":[183],"Together,":[184],"these":[185],"provide":[187],"computational":[190],"workflow":[191],"all":[193],"intermediate":[194],"final":[196],"required":[198],"reproduce":[200],"presented":[203],"in":[204],"accompanying":[206],"publication.":[207]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}