{"id":"https://openalex.org/W7225873152","doi":"https://doi.org/10.21203/rs.3.rs-11275171/v1","title":"Ensemble Method for OCR Error Handling in Early-Modern Japanese Texts","display_name":"Ensemble Method for OCR Error Handling in Early-Modern Japanese Texts","publication_year":2026,"publication_date":"2026-11-12","ids":{"openalex":"https://openalex.org/W7225873152","doi":"https://doi.org/10.21203/rs.3.rs-11275171/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11275171/v1","doi":"https://doi.org/10.21203/rs.3.rs-11275171/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11275171/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21203/rs.3.rs-11275171/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120611725","display_name":"Hiyori Kanetaka","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98885092","display_name":"Nara Women's University","ror":"https://ror.org/05kzadn81","country_code":"JP","type":"education","lineage":["https://openalex.org/I4405286766","https://openalex.org/I98885092"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiyori Kanetaka","raw_affiliation_strings":["Nara Women's University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Women's University","institution_ids":["https://openalex.org/I98885092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100993850","display_name":"Yu Ishikawa","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20442775","display_name":"Kyoto Women's University","ror":"https://ror.org/05ejbda19","country_code":"JP","type":"education","lineage":["https://openalex.org/I20442775"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yu Ishikawa","raw_affiliation_strings":["Kyoto Women's University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto Women's University","institution_ids":["https://openalex.org/I20442775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093842023","display_name":"Miho Chiyonobu","orcid":"https://orcid.org/0009-0000-8043-5079","observed_orcids":["https://orcid.org/0009-0000-8043-5079"]},"institutions":[{"id":"https://openalex.org/I171494771","display_name":"Shiga University","ror":"https://ror.org/01vvhy971","country_code":"JP","type":"education","lineage":["https://openalex.org/I171494771"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miho Chiyonobu","raw_affiliation_strings":["Shiga University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shiga University","institution_ids":["https://openalex.org/I171494771"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149499035","display_name":"Yuki Takemoto","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20442775","display_name":"Kyoto Women's University","ror":"https://ror.org/05ejbda19","country_code":"JP","type":"education","lineage":["https://openalex.org/I20442775"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Takemoto","raw_affiliation_strings":["Kyoto Women's University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto Women's University","institution_ids":["https://openalex.org/I20442775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065240454","display_name":"Masami Takata","orcid":"https://orcid.org/0000-0003-3475-7565","observed_orcids":["https://orcid.org/0000-0003-3475-7565"]},"institutions":[{"id":"https://openalex.org/I98885092","display_name":"Nara Women's University","ror":"https://ror.org/05kzadn81","country_code":"JP","type":"education","lineage":["https://openalex.org/I4405286766","https://openalex.org/I98885092"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masami Takata","raw_affiliation_strings":["Nara Women's University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Women's University","institution_ids":["https://openalex.org/I98885092"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.9951000213623047,"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":0.9951000213623047,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.002300000051036477,"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/T10028","display_name":"Topic Modeling","score":0.0010000000474974513,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792999744415283},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.644599974155426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6171000003814697},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.4666999876499176},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3874000012874603},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.35850000381469727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3531000018119812},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31619998812675476},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11275171/v1","doi":"https://doi.org/10.21203/rs.3.rs-11275171/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11275171/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11275171/v1","doi":"https://doi.org/10.21203/rs.3.rs-11275171/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11275171/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2127141656","https://openalex.org/W2157331557","https://openalex.org/W2962793481","https://openalex.org/W2963341956","https://openalex.org/W3034797320","https://openalex.org/W3094502228","https://openalex.org/W4408925780","https://openalex.org/W4409627033","https://openalex.org/W4416587058","https://openalex.org/W7169529845"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Recently,":[1],"the":[2,20],"digitization":[3],"of":[4,108],"books":[5,17],"has":[6],"been":[7],"actively":[8],"promoted":[9],"to":[10,22,38],"improve":[11],"accessibility.":[12],"However,":[13],"early":[14,23],"modern":[15],"Japanese":[16,70],"published":[18],"from":[19,32],"Meiji":[21],"Showa":[24],"era":[25],"(1868--1935)":[26],"exhibit":[27],"numerous":[28],"characteristics":[29],"that":[30,79,102],"differ":[31],"contemporary":[33],"publications.":[34],"Current":[35],"research":[36],"continues":[37],"advance":[39],"specialized":[40],"character--recognition":[41],"systems":[42],"for":[43,58,91,96],"these":[44],"books.":[45],"Nevertheless,":[46],"recognition":[47],"errors":[48],"remain":[49],"prevalent.":[50],"In":[51],"this":[52],"study,":[53],"we":[54],"introduce":[55],"a":[56,81,89],"method":[57,104],"textual":[59],"error":[60,92,97],"detection":[61],"and":[62,88,113],"correction":[63],"in":[64],"Optical":[65],"Character":[66],"Recognition":[67],"(OCR)--processed":[68],"early--modern":[69],"texts.":[71],"The":[72],"proposed":[73],"approach":[74],"employs":[75],"an":[76,106],"ensemble":[77],"framework":[78],"integrates":[80],"Bidirectional":[82],"Gated":[83],"Recurrent":[84],"Unit":[85],"(Bi--GRU)":[86],"model":[87],"dictionary":[90],"detection,":[93],"alongside":[94],"BERT":[95],"correction.":[98],"Evaluation":[99],"experiments":[100],"demonstrate":[101],"our":[103],"achieves":[105],"F--measure":[107],"\\((74.9%)\\),":[109],"outperforms":[110],"baseline":[111],"methods,":[112],"effectively":[114],"identifies":[115],"erroneous":[116],"characters":[117],"with":[118],"high":[119],"accuracy":[120],"while":[121],"minimizing":[122],"false":[123],"detections.":[124]},"counts_by_year":[],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2026-11-13T00:00:00"}