{"id":"https://openalex.org/W7213428101","doi":"https://doi.org/10.5281/zenodo.22771642","title":"Manchu Unicode HTR for woodblock printing and handwritten Manchu documents from the Qing Period","display_name":"Manchu Unicode HTR for woodblock printing and handwritten Manchu documents from the Qing Period","publication_year":2026,"publication_date":"2026-09-15","ids":{"openalex":"https://openalex.org/W7213428101","doi":"https://doi.org/10.5281/zenodo.22771642"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22771642","doi":"https://doi.org/10.5281/zenodo.22771642","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22771642","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Model"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22771642","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119451170","display_name":"Vincent Paillusson","orcid":"https://orcid.org/0000-0003-1286-3893","observed_orcids":["https://orcid.org/0000-0003-1286-3893"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210092825","display_name":"\u00c9cole Fran\u00e7aise d'Extr\u00eame-Orient","ror":"https://ror.org/00fmnpw63","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210092825"]},{"id":"https://openalex.org/I4387155844","display_name":"Histoire des Th\u00e9ories Linguistiques","ror":"https://ror.org/0546jt497","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I182627622","https://openalex.org/I204730241","https://openalex.org/I4387155844"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Paillusson, Vincent","raw_affiliation_strings":["CNRS UMR 7597 - Laboratoire d'Histoire des th\u00e9ories linguistiques","Ecole fran\u00e7aise d'Extr\u00eame-Orient"],"raw_orcid":"https://orcid.org/0000-0003-1286-3893","affiliations":[{"raw_affiliation_string":"CNRS UMR 7597 - Laboratoire d'Histoire des th\u00e9ories linguistiques","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4387155844"]},{"raw_affiliation_string":"Ecole fran\u00e7aise d'Extr\u00eame-Orient","institution_ids":["https://openalex.org/I4210092825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102974323","display_name":"Michela Bussotti","orcid":"https://orcid.org/0000-0003-2124-6555","observed_orcids":["https://orcid.org/0000-0003-2124-6555"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"BUSSOTTI, MICHELA","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2124-6555","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101952885","display_name":"El\u00f6d Egyed\u2010Zsigmond","orcid":"https://orcid.org/0000-0002-1218-8026","observed_orcids":["https://orcid.org/0000-0002-1218-8026"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"EGYED-ZSIGMOND, El\u00f6d","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1218-8026","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054721330","display_name":"Hsiang-Tai Kao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210092825","display_name":"\u00c9cole Fran\u00e7aise d'Extr\u00eame-Orient","ror":"https://ror.org/00fmnpw63","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210092825"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Kao, Hsiang-Tai","raw_affiliation_strings":["\u00c9cole Fran\u00e7aise d'Extr\u00eame-Orient"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole Fran\u00e7aise d'Extr\u00eame-Orient","institution_ids":["https://openalex.org/I4210092825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012362955","display_name":"Alice Crowther","orcid":"https://orcid.org/0009-0003-0616-1841","observed_orcids":["https://orcid.org/0009-0003-0616-1841"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Crowther, Alice","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0003-0616-1841","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5119451168","display_name":"Shad Mohammad","orcid":"https://orcid.org/0000-0002-8266-6011","observed_orcids":["https://orcid.org/0000-0002-8266-6011"]},"institutions":[{"id":"https://openalex.org/I34476706","display_name":"DHA Suffa University","ror":"https://ror.org/01fyxr563","country_code":"PK","type":"education","lineage":["https://openalex.org/I34476706"]},{"id":"https://openalex.org/I4210093622","display_name":"Indus University","ror":"https://ror.org/00hqpmg61","country_code":"PK","type":"education","lineage":["https://openalex.org/I4210093622"]},{"id":"https://openalex.org/I48430043","display_name":"Institut National des Sciences Appliqu\u00e9es de Lyon","ror":"https://ror.org/050jn9y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I203339264","https://openalex.org/I48430043"]},{"id":"https://openalex.org/I70764227","display_name":"Indus University","ror":"https://ror.org/03ehk1n67","country_code":"IN","type":"education","lineage":["https://openalex.org/I70764227"]}],"countries":["FR","IN","PK"],"is_corresponding":false,"raw_author_name":"Mohammad, Shad","raw_affiliation_strings":["Institut National des Sciences Appliqu\u00e9es de Lyon","Indus University","DHA Suffa University"],"raw_orcid":"https://orcid.org/0000-0002-8266-6011","affiliations":[{"raw_affiliation_string":"Institut National des Sciences Appliqu\u00e9es de Lyon","institution_ids":["https://openalex.org/I48430043"]},{"raw_affiliation_string":"Indus University","institution_ids":["https://openalex.org/I4210093622","https://openalex.org/I70764227"]},{"raw_affiliation_string":"DHA Suffa University","institution_ids":["https://openalex.org/I34476706"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/manchu","display_name":"Manchu language","score":0.875},{"id":"https://openalex.org/keywords/handwriting-recognition","display_name":"handwriting recognition","score":0.6019999980926514},{"id":"https://openalex.org/keywords/woodblock-printing","display_name":"wood engraving","score":0.9430000185966492},{"id":"https://openalex.org/keywords/manchu-manuscripts","display_name":"Manchu manuscripts","score":0.46700000762939453},{"id":"https://openalex.org/keywords/character-recognition","display_name":"character recognition","score":0.40700000524520874}],"concepts":[{"id":"https://openalex.org/C500551929","wikidata":"https://www.wikidata.org/wiki/Q8819","display_name":"Unicode","level":2,"score":0.8569999933242798},{"id":"https://openalex.org/C2781291010","wikidata":"https://www.wikidata.org/wiki/Q178580","display_name":"Period (music)","level":2,"score":0.6499999761581421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5902000069618225},{"id":"https://openalex.org/C2779120887","wikidata":"https://www.wikidata.org/wiki/Q814722","display_name":"Participle","level":3,"score":0.5435000061988831},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5178999900817871},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5170999765396118},{"id":"https://openalex.org/C106930687","wikidata":"https://www.wikidata.org/wiki/Q976327","display_name":"Romanization","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4108999967575073},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3939000070095062},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3407000005245209},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.319599986076355},{"id":"https://openalex.org/C146778888","wikidata":"https://www.wikidata.org/wiki/Q836862","display_name":"Installation","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2992999851703644},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25440001487731934},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22771642","doi":"https://doi.org/10.5281/zenodo.22771642","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22771642","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Model"},{"id":"doi:10.5281/zenodo.22771643","doi":"https://doi.org/10.5281/zenodo.22771643","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22771643","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Model"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22771642","doi":"https://doi.org/10.5281/zenodo.22771642","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22771642","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Model"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7154409428","https://openalex.org/W7112326331","https://openalex.org/W7116793138","https://openalex.org/W7203822781","https://openalex.org/W4413416477","https://openalex.org/W6954993550","https://openalex.org/W4365396060","https://openalex.org/W2532570605","https://openalex.org/W7118452877","https://openalex.org/W7212297268"],"abstract_inverted_index":{"Manchu":[0,43],"unicode":[1,44],"HTR":[2],"model":[3,11,57,64,80,111,122,142],"for":[4,58,143],"manchu":[5,21,82,85],"This":[6,63],"is":[7,123],"a":[8,46,55,126,140],"text":[9],"recognition":[10],"trained":[12,66,124],"on":[13,125,160],"242":[14],"transcribed":[15,35],"pages":[16,33],"(~3000":[17],"lines)":[18],"from":[19,148,165],"five":[20],"documents":[22,97,128],"(xylographic":[23],"and":[24,39,76,113,162],"handwritten)":[25],"made":[26],"during":[27,67],"the":[28,51,68,73,92,155,158,166],"Qing":[29],"period":[30],"(1644-1911).":[31],"Those":[32],"were":[34,40],"using":[36,45,91,163],"M\u00f6llendorf":[37],"romanisation":[38],"converted":[41],"into":[42,84],"Python":[47],"script,":[48],"hence":[49],"giving":[50],"opportunity":[52],"to":[53,151],"train":[54],"dedicated":[56],"transcribing":[59],"directly":[60],"in":[61],"Manchu.":[62],"was":[65],"ManjugisunTranscript":[69],"Project":[70],"funded":[71],"by":[72],"BnF":[74],"Datalab":[75],"Huma-Num":[77],"(2025-2026).":[78],"The":[79,109,121],"transcribe":[81],"script":[83],"Unicode.":[86],"Punctuations":[87],"marks":[88],"are":[89],"rendered":[90],"latin":[93],"characters.":[94],"List":[95],"of":[96,115],"mandchou":[98,100,102,104,106],"117":[99],"243":[101],"289":[103],"168":[105],"268":[107],"Architecture":[108],"default":[110],"architecture":[112],"hyperparameters":[114],"kraken":[116,164],"6.0":[117],"where":[118],"used.":[119],"Uses":[120],"xylographic":[127],"as":[129,131,139],"well":[130,132],"written":[133],"manuscripts.":[134],"It":[135],"can":[136],"be":[137],"used":[138],"base":[141],"fine-tuning":[144],"more":[145],"specific":[146],"models":[147],"it.":[149],"How":[150],"Get":[152],"Started":[153],"with":[154],"Model":[156],"Follow":[157],"instructions":[159],"installing":[161],"website.":[167],"Metrics":[168],"CER:":[169],"2%":[170]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-17T00:00:00"}
