{"id":"https://openalex.org/W7204135291","doi":"https://doi.org/10.25592/uhhfdm.19255","title":"What transcription approach HTR should learn? HTR, Normalization, and Editorial Tradition in Medieval Manuscript Studies","display_name":"What transcription approach HTR should learn? HTR, Normalization, and Editorial Tradition in Medieval Manuscript Studies","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204135291","doi":"https://doi.org/10.25592/uhhfdm.19255"},"language":"en","primary_location":{"id":"pmh:doi:10.25592/uhhfdm.19255","doi":null,"is_oa":true,"landing_page_url":"https://www.fdr.uni-hamburg.de/record/10.25592/uhhfdm.19255","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Conference paper"},"volume":null,"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.fdr.uni-hamburg.de/record/10.25592/uhhfdm.19255","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147995367","display_name":"Anna Michalcov\u00e1","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I202391551","display_name":"Czech Academy of Sciences","ror":"https://ror.org/053avzc18","country_code":"CZ","type":"government","lineage":["https://openalex.org/I202391551"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Anna Michalcov\u00e1","raw_affiliation_strings":["Czech Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Academy of Sciences","institution_ids":["https://openalex.org/I202391551"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058090899","display_name":"Jan Odstr\u010dil\u00edk","orcid":"https://orcid.org/0000-0001-9104-9827","observed_orcids":["https://orcid.org/0000-0001-9104-9827"]},"institutions":[{"id":"https://openalex.org/I138211613","display_name":"Austrian Academy of Sciences","ror":"https://ror.org/03anc3s24","country_code":"AT","type":"government","lineage":["https://openalex.org/I138211613"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Jan Odstr\u010dil\u00edk","raw_affiliation_strings":["\u00d6sterreichischen Akademie der Wissenschaften"],"raw_orcid":"https://orcid.org/0000-0001-9104-9827","affiliations":[{"raw_affiliation_string":"\u00d6sterreichischen Akademie der Wissenschaften","institution_ids":["https://openalex.org/I138211613"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75230364,"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":false,"primary_topic":{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.861299991607666,"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"}},"topics":[{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.861299991607666,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.13050000369548798,"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/T14170","display_name":"Classical Studies and Philology","score":0.0024999999441206455,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"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/handwriting-recognition","display_name":"handwriting recognition","score":0.7829999923706055},{"id":"https://openalex.org/keywords/diplomatic-transcription","display_name":"diplomatic transcription","score":0.6079999804496765},{"id":"https://openalex.org/keywords/normalization","display_name":"normalization","score":0.5149999856948853},{"id":"https://openalex.org/keywords/editorial-tradition","display_name":"editorial tradition","score":0.781000018119812},{"id":"https://openalex.org/keywords/medieval-manuscripts","display_name":"medieval manuscripts","score":0.8730000257492065},{"id":"https://openalex.org/keywords/paleography","display_name":"paleography","score":0.5989999771118164},{"id":"https://openalex.org/keywords/orthographic-standardization","display_name":"orthographic standardization","score":0.6579999923706055},{"id":"https://openalex.org/keywords/transliteration","display_name":"transliteration","score":0.843999981880188},{"id":"https://openalex.org/keywords/script-conversion","display_name":"script conversion","score":0.4269999861717224},{"id":"https://openalex.org/keywords/historical-corpora","display_name":"historical corpora","score":0.45399999618530273},{"id":"https://openalex.org/keywords/philology","display_name":"philology","score":0.3779999911785126},{"id":"https://openalex.org/keywords/medieval-german","display_name":"medieval German","score":0.382999986410141},{"id":"https://openalex.org/keywords/latin-manuscripts","display_name":"Latin manuscripts","score":0.3889999985694885},{"id":"https://openalex.org/keywords/medieval-spanish-manuscripts","display_name":"medieval Spanish manuscripts","score":0.4480000138282776},{"id":"https://openalex.org/keywords/medieval-italian-manuscripts","display_name":"medieval Italian manuscripts","score":0.5009999871253967},{"id":"https://openalex.org/keywords/medieval-hebrew-manuscripts","display_name":"medieval Hebrew manuscripts","score":0.47999998927116394},{"id":"https://openalex.org/keywords/medieval-arabic-manuscripts","display_name":"medieval Arabic manuscripts","score":0.5509999990463257}],"concepts":[{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7760000228881836},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.559499979019165},{"id":"https://openalex.org/C60940604","wikidata":"https://www.wikidata.org/wiki/Q179957","display_name":"Palaeography","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C2779137862","wikidata":"https://www.wikidata.org/wiki/Q425951","display_name":"Capitalization","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4156999886035919},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35519999265670776},{"id":"https://openalex.org/C74916050","wikidata":"https://www.wikidata.org/wiki/Q841090","display_name":"Classics","level":1,"score":0.35030001401901245},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.3346000015735626},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C23987474","wikidata":"https://www.wikidata.org/wiki/Q40634","display_name":"Philology","level":3,"score":0.3111000061035156},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.2590999901294708},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.25369998812675476}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:doi:10.25592/uhhfdm.19255","doi":null,"is_oa":true,"landing_page_url":"https://www.fdr.uni-hamburg.de/record/10.25592/uhhfdm.19255","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"pmh:doi:10.25592/uhhfdm.19256","doi":null,"is_oa":true,"landing_page_url":"https://www.fdr.uni-hamburg.de/record/10.25592/uhhfdm.19256","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"doi:10.25592/uhhfdm.19255","doi":"https://doi.org/10.25592/uhhfdm.19255","is_oa":true,"landing_page_url":"https://doi.org/10.25592/uhhfdm.19255","pdf_url":null,"source":{"id":"https://openalex.org/S7407052903","display_name":"Universit\u00e4t Hamburg","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I159176309","host_organization_name":"Universit\u00e4t Hamburg","host_organization_lineage":["https://openalex.org/I159176309"],"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"},{"id":"doi:10.25592/uhhfdm.19256","doi":"https://doi.org/10.25592/uhhfdm.19256","is_oa":true,"landing_page_url":"https://doi.org/10.25592/uhhfdm.19256","pdf_url":null,"source":{"id":"https://openalex.org/S7407052903","display_name":"Universit\u00e4t Hamburg","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I159176309","host_organization_name":"Universit\u00e4t Hamburg","host_organization_lineage":["https://openalex.org/I159176309"],"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:doi:10.25592/uhhfdm.19255","doi":null,"is_oa":true,"landing_page_url":"https://www.fdr.uni-hamburg.de/record/10.25592/uhhfdm.19255","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Conference paper"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.51298987865448,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Extended":[0],"abstract":[1],"accepted":[2],"for":[3,34],"the":[4,105,151,155,176,202,212,229,254,267,303,313,318,365,382,392],"International":[5],"Workshop":[6,39,53],"on":[7,85,201,211,364],"Computational":[8],"Paleography":[9],"(IWCP":[10],"2026,":[11,16,23],"4th":[12],"edition),":[13,324],"4":[14],"September":[15],"Vienna,":[17],"Austria,":[18],"a":[19,26,29,86,94,182,293],"workshop":[20],"of":[21,61,66,104,123,142,169,253,256,278,296,305,317,322,367,394],"ICDAR":[22],"presented":[24],"as":[25,144,228],"poster":[27],"with":[28,77,119,132,217,264],"flash":[30],"presentation.":[31],"Published":[32],"here":[33],"open":[35],"access":[36],"and":[37,226,246,275,325,343,376,400],"citation.":[38],"Organisers:":[40],"Isabelle":[41],"Marthot-Santaniello,":[42],"Universit\u00e4t":[43,49],"Basel,":[44,45],"Switzerland":[46],"Hussein":[47],"Mohammed,":[48],"Hamburg,":[50,51],"Germany":[52],"page:":[54],"IWCP":[55],"2026":[56],":":[57,59],"CSMC":[58],"University":[60],"Hamburg":[62],"The":[63],"growing":[64],"use":[65],"Handwritten":[67],"Text":[68],"Recognition":[69],"(HTR)":[70],"tools":[71],"radically":[72],"changes":[73],"how":[74,116],"scholars":[75],"engage":[76],"historical":[78,265,306],"corpora,":[79],"enabling":[80],"them":[81,385],"to":[82,158,207,215,302,335,348],"process":[83],"manuscripts":[84],"much":[87],"larger":[88],"scale":[89],"than":[90],"ever":[91],"before.":[92],"As":[93],"natural":[95],"side-effect,":[96],"HTR":[97,117,134,186,193,280,395],"also":[98,310],"creates":[99],"new":[100],"methodological":[101,285,362],"challenges.":[102],"One":[103],"major":[106],"ones,":[107,161],"which":[108,308],"hasn't":[109],"been":[110],"discussed":[111],"extensively":[112],"so":[113],"far,":[114],"is,":[115],"interacts":[118],"long-standing":[120],"philological":[121],"practices":[122,252],"various":[124,257,298],"languages,":[125],"influences":[126],"them,":[127],"or":[128,173,339,352],"is":[129,191,209,235,270],"in":[130,391],"conflict":[131],"them.":[133],"can":[135],"be":[136],"theoretically":[137],"trained":[138,200],"using":[139],"any":[140],"type":[141],"transcription":[143,152,304,319],"ground":[145,396],"truth:":[146],"from":[147,333],"hyperdiplomatic":[148,268],"\u2013":[149,157,370,379],"where":[150],"closely":[153,205],"follows":[154],"original":[156],"very":[159,336],"interpretative":[160],"that,":[162],"e.g.,":[163],"expand":[164],"automatically":[165],"abbreviations,":[166],"normalize":[167],"capitalization":[168],"letters,":[170],"standardise":[171],"orthography,":[172],"even":[174,340],"change":[175],"script.":[177],"Recently,":[178],"we":[179,329],"have":[180,290],"seen":[181],"push":[183],"towards":[184],"(hyper)diplomatic":[185,240,279],"models.":[187],"A":[188],"common":[189,271],"argument":[190],"that":[192,204,238,247,381],"models":[194],"work":[195],"best":[196,250],"if":[197],"they":[198,248],"are":[199,309],"data":[203],"correspond":[206],"what":[208],"present":[210],"page,":[213],"character":[214],"character,":[216],"only":[218],"occasional":[219],"small":[220],"compromises":[221],"(e.g.,":[222,272],"transcribing":[223],"allographs":[224],"\"s\"":[225,231],"\"\u017f\"":[227],"same":[230],"character).":[232],"Additionally,":[233],"it":[234],"being":[236],"argued":[237],"such":[239],"transcriptions":[241],"may":[242,330],"enable":[243],"palaeographic":[244],"inquiry,":[245],"follow":[249],"DH":[251],"separation":[255],"concerns.":[258],"For":[259],"some":[260],"philologies,":[261],"when":[262],"working":[263],"manuscripts,":[266,307],"approach":[269],"medieval":[273,371,377],"German),":[274],"thus":[276],"adoption":[277],"systems":[281],"does":[282],"not":[283],"cause":[284],"tensions.":[286],"However,":[287],"other":[288],"philologies":[289],"developed":[291],"over":[292],"long":[294],"period":[295],"time":[297],"substantially":[299],"different":[300,354],"approaches":[301],"influenced":[311],"by":[312],"research":[314,344],"question,":[315],"purpose":[316],"(e.g.":[320],"preparation":[321],"an":[323],"local":[326],"conventions.":[327],"Thus":[328],"see":[331],"anything":[332],"semi-diplomatic":[334],"normalized":[337],"transcriptions,":[338],"highly":[341],"sophisticated":[342],"based":[345],"silent":[346],"conversions":[347],"modern":[349],"orthographical":[350],"system":[351],"intoa":[353],"script":[355],"(so-called":[356],"\u201ctransliteration\u201d).":[357],"Our":[358],"contribution":[359],"analyzes":[360],"this":[361],"tension":[363],"example":[366],"two":[368],"distinctphilologies":[369],"Latin":[372],"(especially":[373],"Late":[374],"medieval)":[375],"Czech":[378],"arguing":[380],"contrast":[383],"between":[384],"illuminates":[386],"broader,":[387],"underexamined":[388],"assumptions":[389],"embedded":[390],"design":[393],"truth,":[397],"evaluation":[398],"metrics,":[399],"post":[401],"correction":[402],"workflows.":[403]},"counts_by_year":[],"updated_date":"2026-10-07T09:51:55.459714","created_date":"2026-08-25T00:00:00"}
