{"id":"https://openalex.org/W3084407320","doi":null,"title":"Books of Hours: the First Liturgical Corpus for Text Segmentation","display_name":"Books of Hours: the First Liturgical Corpus for Text Segmentation","publication_year":2020,"publication_date":"2020-05-11","ids":{"openalex":"https://openalex.org/W3084407320","mag":"3084407320"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-02931294v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-02931294","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"12th Language Resources and Evaluation Conference, May 2020, Marseille (Virtual), France. pp.776-784","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-02931294","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112027771","display_name":"Amir Hazem","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210117005","display_name":"Laboratoire des Sciences du Num\u00e9rique de Nantes","ror":"https://ror.org/02snf8m58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100445878","https://openalex.org/I1294671590","https://openalex.org/I205703379","https://openalex.org/I4210117005","https://openalex.org/I4210124215","https://openalex.org/I4210127572","https://openalex.org/I4210139971","https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Hazem, Amir","raw_affiliation_strings":["Laboratoire des Sciences du Num\u00e9rique de Nantes","Traitement Automatique du Langage Naturel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire des Sciences du Num\u00e9rique de Nantes","institution_ids":["https://openalex.org/I4210117005"]},{"raw_affiliation_string":"Traitement Automatique du Langage Naturel","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026850687","display_name":"B\u00e9atrice Daille","orcid":"https://orcid.org/0000-0001-9095-7372","observed_orcids":["https://orcid.org/0000-0001-9095-7372"]},"institutions":[{"id":"https://openalex.org/I4210117005","display_name":"Laboratoire des Sciences du Num\u00e9rique de Nantes","ror":"https://ror.org/02snf8m58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100445878","https://openalex.org/I1294671590","https://openalex.org/I205703379","https://openalex.org/I4210117005","https://openalex.org/I4210124215","https://openalex.org/I4210127572","https://openalex.org/I4210139971","https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Daille, B\u00e9atrice","raw_affiliation_strings":["Laboratoire des Sciences du Num\u00e9rique de Nantes","Traitement Automatique du Langage Naturel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire des Sciences du Num\u00e9rique de Nantes","institution_ids":["https://openalex.org/I4210117005"]},{"raw_affiliation_string":"Traitement Automatique du Langage Naturel","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065746112","display_name":"Marie-Laurence Bonhomme","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bonhomme, Marie-Laurence","raw_affiliation_strings":["Teklia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Teklia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083359437","display_name":"Martin Maarand","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maarand, Martin","raw_affiliation_strings":["Teklia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Teklia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051073934","display_name":"M\u00e9lodie Boillet","orcid":"https://orcid.org/0000-0002-0618-7852","observed_orcids":["https://orcid.org/0000-0002-0618-7852"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boillet, M\u00e9lodie","raw_affiliation_strings":["Teklia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Teklia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024834377","display_name":"Christopher Kermorvant","orcid":"https://orcid.org/0000-0002-7508-4080","observed_orcids":["https://orcid.org/0000-0002-7508-4080"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kermorvant, Christopher","raw_affiliation_strings":["A2iA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A2iA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010004183","display_name":"Dominique Stutzmann","orcid":"https://orcid.org/0000-0003-3705-5825","observed_orcids":["https://orcid.org/0000-0003-3705-5825"]},"institutions":[{"id":"https://openalex.org/I4210156313","display_name":"Institut de Recherche et d'Histoire des Textes","ror":"https://ror.org/05evznf71","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210150854","https://openalex.org/I4210156313"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stutzmann, Dominique","raw_affiliation_strings":["Institut de recherche et d'histoire des textes"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut de recherche et d'histoire des textes","institution_ids":["https://openalex.org/I4210156313"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0741,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.31508063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"776","last_page":"784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9961000084877014,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9961000084877014,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.0034000000450760126,"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/T14386","display_name":"Libraries, Manuscripts, and Books","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1202","display_name":"History"},"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/books-of-hours","display_name":"books of hours","score":0.9509999752044678},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"text segmentation","score":0.9449999928474426},{"id":"https://openalex.org/keywords/handwriting-recognition","display_name":"handwriting recognition","score":0.8880000114440918},{"id":"https://openalex.org/keywords/latin-transcription","display_name":"Latin transcription","score":0.6389999985694885},{"id":"https://openalex.org/keywords/liturgical-books","display_name":"liturgical texts","score":0.5239999890327454},{"id":"https://openalex.org/keywords/medieval-manuscripts","display_name":"medieval manuscripts","score":0.5730000138282776},{"id":"https://openalex.org/keywords/annotated-corpora","display_name":"annotated corpus","score":0.527999997138977},{"id":"https://openalex.org/keywords/religious-devotion","display_name":"religious devotion","score":0.6230000257492065},{"id":"https://openalex.org/keywords/multilingual-manuscripts","display_name":"multilingual manuscripts","score":0.4659999907016754},{"id":"https://openalex.org/keywords/illuminated-manuscripts","display_name":"illuminated manuscripts","score":0.32199999690055847}],"concepts":[{"id":"https://openalex.org/C2776084483","wikidata":"https://www.wikidata.org/wiki/Q272937","display_name":"Treasure","level":2,"score":0.57509446144104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5689821243286133},{"id":"https://openalex.org/C52069626","wikidata":"https://www.wikidata.org/wiki/Q4692","display_name":"The Renaissance","level":2,"score":0.5686731338500977},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5368953347206116},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5321295261383057},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5273888111114502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5244572162628174},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.503128707408905},{"id":"https://openalex.org/C143128703","wikidata":"https://www.wikidata.org/wiki/Q12554","display_name":"Middle Ages","level":2,"score":0.4724961817264557},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4610111117362976},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.43068766593933105},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.38397377729415894},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2823285460472107},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.21191635727882385},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.20619526505470276},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07786941528320312},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.06882259249687195},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.06742429733276367},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:HAL:hal-02931294v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-02931294","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"12th Language Resources and Evaluation Conference, May 2020, Marseille (Virtual), France. pp.776-784","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-02931294v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-02931294","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"12th Language Resources and Evaluation Conference, May 2020, Marseille (Virtual), France. pp.776-784","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W560118347","https://openalex.org/W589624688","https://openalex.org/W1557074680","https://openalex.org/W1567616047","https://openalex.org/W1626945812","https://openalex.org/W1710422233","https://openalex.org/W1828401780","https://openalex.org/W1862888253","https://openalex.org/W1894075015","https://openalex.org/W1983814883","https://openalex.org/W2039500607","https://openalex.org/W2098337925","https://openalex.org/W2100873065","https://openalex.org/W2106918957","https://openalex.org/W2118612506","https://openalex.org/W2148818577","https://openalex.org/W2149041454","https://openalex.org/W2149508209","https://openalex.org/W2159083595","https://openalex.org/W2172125983","https://openalex.org/W2509596028","https://openalex.org/W2794904608","https://openalex.org/W2807938752","https://openalex.org/W2808114373","https://openalex.org/W2896419327","https://openalex.org/W2963041453","https://openalex.org/W3003285202","https://openalex.org/W3114937213"],"related_works":["https://openalex.org/W3114157502","https://openalex.org/W3088047859","https://openalex.org/W2981213555","https://openalex.org/W4415288630","https://openalex.org/W7134865188","https://openalex.org/W7096812964","https://openalex.org/W4414860026","https://openalex.org/W2126530112","https://openalex.org/W4323921551","https://openalex.org/W6927128684"],"abstract_inverted_index":{"The":[0],"Book":[1],"of":[2,7,23,41,60,62,98,122,124,128,131,134,160,163,170,181,185],"Hours":[3],"was":[4],"the":[5,8,26,58,119,161,182,186],"bestseller":[6],"late":[9,27],"Middle":[10,28],"Ages":[11],"and":[12,46,152,165],"Renaissance.":[13],"It":[14],"is":[15,143],"a":[16,157,178],"historical":[17,113],"invaluable":[18],"treasure,":[19],"documentingthe":[20],"devotional":[21],"practices":[22],"Christians":[24],"in":[25,67,85,104],"Ages.":[29],"Up":[30],"to":[31,83,173],"now,":[32],"its":[33,44,47,70,91,107],"textual":[34,108],"content":[35,109],"has":[36],"been":[37],"scarcely":[38],"studied":[39],"because":[40],"itsmanuscript":[42],"nature,":[43],"length":[45],"complex":[48],"content.":[49],"At":[50],"first":[51,120],"glance,":[52],"it":[53],"looks":[54],"too":[55],"standardized.":[56],"However,":[57],"study":[59],"book":[61,162],"hoursraises":[63],"important":[64],"challenges:":[65],"(i)":[66],"image":[68],"analysis,":[69],"often":[71],"lavish":[72],"ornamentation":[73],"(illegible":[74],"painted":[75],"initials,":[76],"line-fillers,":[77],"etc.),":[78],"abbreviatedwords,":[79],"multilingualism":[80],"are":[81],"difficult":[82],"address":[84],"Handwritten":[86],"Text":[87,138],"Recognition":[88,139,147],"(HTR);":[89],"(ii)":[90],"hierarchical":[92],"entangled":[93],"structure":[94],"offers":[95],"anew":[96],"field":[97],"investigation":[99],"for":[100,112,150],"text":[101,188],"segmentation;":[102],"(iii)":[103],"digital":[105],"humanities,":[106],"gives":[110],"opportunities":[111],"analysis.In":[114],"this":[115,174],"paper,":[116],"we":[117],"provide":[118],"corpus":[121],"books":[123,133,169],"hours,":[125],"which":[126],"consists":[127],"Latin":[129],"transcriptions":[130],"300":[132],"hours":[135,164,171],"generated":[136],"byHandwritten":[137],"(HTR)":[140],"-":[141],"that":[142],"like":[144],"Optical":[145],"Character":[146],"(OCR)":[148],"but":[149],"handwritten":[151],"not":[153],"printed":[154],"texts.":[155],"Wedesigned":[156],"structural":[158],"scheme":[159],"annotated":[166],"manually":[167],"two":[168],"according":[172],"scheme.":[175],"Lastly,":[176],"weperformed":[177],"systematic":[179],"evaluation":[180],"main":[183],"state":[184],"art":[187],"segmentation":[189],"approache":[190]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2020-09-14T00:00:00"}
