{"id":"https://openalex.org/W6929657216","doi":"https://doi.org/10.48694/jcls.3924","title":"BookNLP-fr, the French Versant of BookNLP. A Tailored Pipeline for 19th and 20th Century French Literature","display_name":"BookNLP-fr, the French Versant of BookNLP. A Tailored Pipeline for 19th and 20th Century French Literature","publication_year":2024,"publication_date":"2024-11-21","ids":{"openalex":"https://openalex.org/W6929657216","doi":"https://doi.org/10.48694/jcls.3924"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-04838805v1","is_oa":true,"landing_page_url":"https://cnrs.hal.science/hal-04838805","pdf_url":"https://cnrs.hal.science/hal-04838805/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Journal of Computational Literary Studies, 2024, 3 (1), pp.1-34. &#x27E8;10.48694/jcls.3924&#x27E9;","raw_type":"Journal articles"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://cnrs.hal.science/hal-04838805/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Fr\u00e9d\u00e9rique M\u00e9lanie-Becquet","orcid":null},"institutions":[{"id":"https://openalex.org/I116921496","display_name":"Lattice Semiconductor (United States)","ror":"https://ror.org/01hght844","country_code":"US","type":"company","lineage":["https://openalex.org/I116921496"]},{"id":"https://openalex.org/I4210134114","display_name":"Langues, Textes, Traitements Informatiques, Cognition","ror":"https://ror.org/03ms1y683","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I182627622","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210134114","https://openalex.org/I4210150854"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Fr\u00e9d\u00e9rique M\u00e9lanie-Becquet","raw_affiliation_strings":["Lattice UMR8094"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lattice UMR8094","institution_ids":["https://openalex.org/I116921496","https://openalex.org/I4210134114"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jean Barr\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I116921496","display_name":"Lattice Semiconductor (United States)","ror":"https://ror.org/01hght844","country_code":"US","type":"company","lineage":["https://openalex.org/I116921496"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jean Barr\u00e9","raw_affiliation_strings":["LATTICE, ENS-PSL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LATTICE, ENS-PSL","institution_ids":["https://openalex.org/I116921496"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Olga Seminck","orcid":null},"institutions":[{"id":"https://openalex.org/I116921496","display_name":"Lattice Semiconductor (United States)","ror":"https://ror.org/01hght844","country_code":"US","type":"company","lineage":["https://openalex.org/I116921496"]},{"id":"https://openalex.org/I4210134114","display_name":"Langues, Textes, Traitements Informatiques, Cognition","ror":"https://ror.org/03ms1y683","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I182627622","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210134114","https://openalex.org/I4210150854"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Olga Seminck","raw_affiliation_strings":["Lattice UMR8094"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lattice UMR8094","institution_ids":["https://openalex.org/I116921496","https://openalex.org/I4210134114"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cl\u00e9ment Plancq","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cl\u00e9ment Plancq","raw_affiliation_strings":[""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Marco Naguib","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Naguib","raw_affiliation_strings":[""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Martial Pastor","orcid":null},"institutions":[{"id":"https://openalex.org/I1299319934","display_name":"Rijksmuseum","ror":"https://ror.org/006wjwp03","country_code":"NL","type":"archive","lineage":["https://openalex.org/I1299319934"]},{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Martial Pastor","raw_affiliation_strings":["Rijksuniversiteit Groningen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rijksuniversiteit Groningen","institution_ids":["https://openalex.org/I1299319934","https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":null,"display_name":"Thierry Poibeau","orcid":null},"institutions":[{"id":"https://openalex.org/I116921496","display_name":"Lattice Semiconductor (United States)","ror":"https://ror.org/01hght844","country_code":"US","type":"company","lineage":["https://openalex.org/I116921496"]},{"id":"https://openalex.org/I4210134114","display_name":"Langues, Textes, Traitements Informatiques, Cognition","ror":"https://ror.org/03ms1y683","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I182627622","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210134114","https://openalex.org/I4210150854"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Thierry Poibeau","raw_affiliation_strings":["Lattice UMR 8094, ENS-PSL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lattice UMR 8094, ENS-PSL","institution_ids":["https://openalex.org/I116921496","https://openalex.org/I4210134114"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36423738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.19619999825954437,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.19619999825954437,"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/T13629","display_name":"Text Readability and Simplification","score":0.15080000460147858,"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":0.11710000038146973,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.8788999915122986},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6452000141143799},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6345000267028809},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6274999976158142},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5950000286102295}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8788999915122986},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6452000141143799},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6345000267028809},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6274999976158142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5965999960899353},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5950000286102295},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5698999762535095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46970000863075256},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3862999975681305},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35109999775886536},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31839999556541443},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:HAL:hal-04838805v1","is_oa":true,"landing_page_url":"https://cnrs.hal.science/hal-04838805","pdf_url":"https://cnrs.hal.science/hal-04838805/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Journal of Computational Literary Studies, 2024, 3 (1), pp.1-34. &#x27E8;10.48694/jcls.3924&#x27E9;","raw_type":"Journal articles"},{"id":"doi:10.48694/jcls.3924","is_oa":true,"landing_page_url":"https://doi.org/10.48694/jcls.3924","pdf_url":null,"source":{"id":"https://openalex.org/S7407051653","display_name":"TUjournals","issn_l":null,"issn":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04838805v1","is_oa":true,"landing_page_url":"https://cnrs.hal.science/hal-04838805","pdf_url":"https://cnrs.hal.science/hal-04838805/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Journal of Computational Literary Studies, 2024, 3 (1), pp.1-34. &#x27E8;10.48694/jcls.3924&#x27E9;","raw_type":"Journal articles"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.9034716486930847}],"awards":[{"id":"https://openalex.org/G1207471641","display_name":null,"funder_award_id":"ANR-19-P3IA0001","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5838787665","display_name":"PaRis Artificial Intelligence Research InstitutE","funder_award_id":"ANR-19-P3IA-0001","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8318455765","display_name":null,"funder_award_id":"ANR-19","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W6929657216.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,128],"paper":[1],"presents":[2],"BookNLP-fr:":[3],"the":[4,25,29,40,48,60,101,130,139],"adaptation":[5,30],"to":[6,35,43,47,95,110,119,132],"French":[7],"of":[8,24,31,50,53,67,123,141],"BookNLP,":[9],"an":[10,22],"existing":[11],"NLP":[12,107],"pipeline":[13,34],"tailored":[14],"for":[15,73],"literary":[16,75,136],"texts":[17],"in":[18,28,126],"English.":[19],"We":[20,79],"provide":[21],"overview":[23],"challenges":[26,41],"involved":[27],"such":[32],"a":[33,36,70,111,116,134],"new":[37,117],"language:":[38],"from":[39],"related":[42],"data":[44],"annotation":[45],"up":[46],"development":[49],"specialized":[51],"modules":[52],"entity":[54],"recognition":[55],"and":[56,86,114],"coreference.":[57],"Moving":[58],"beyond":[59],"technical":[61],"aspects,":[62],"we":[63],"explore":[64],"practical":[65],"applications":[66],"BookNLP-fr":[68,82,105],"with":[69],"canonical":[71],"task":[72],"computational":[74],"studies:":[76],"subgenre":[77,98],"classification.":[78],"show":[80],"that":[81],"provides":[83],"more":[84,89,92],"relevant":[85],"--":[87,91],"even":[88],"importantly":[90],"interpretable":[93],"features":[94],"perform":[96],"automatic":[97],"classification":[99],"than":[100],"traditional":[102],"\\textit{bag-of-words}":[103],"approach.":[104],"makes":[106],"techniques":[108],"available":[109],"larger":[112],"public":[113],"constitutes":[115],"toolkit":[118],"process":[120],"large":[121],"numbers":[122],"digitized":[124],"books":[125],"French.":[127],"allows":[129],"field":[131],"gain":[133],"deeper":[135],"understanding":[137],"through":[138],"practice":[140],"distant":[142],"reading.":[143]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}
