{"id":"https://openalex.org/W4407832567","doi":"https://doi.org/10.1007/s00799-025-00415-x","title":"Post-ocr text correction for Bulgarian historical documents","display_name":"Post-ocr text correction for Bulgarian historical documents","publication_year":2025,"publication_date":"2025-02-21","ids":{"openalex":"https://openalex.org/W4407832567","doi":"https://doi.org/10.1007/s00799-025-00415-x"},"language":"en","primary_location":{"id":"doi:10.1007/s00799-025-00415-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00799-025-00415-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00799-025-00415-x.pdf","source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00799-025-00415-x.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052702364","display_name":"Angel Beshirov","orcid":"https://orcid.org/0000-0002-0684-2730"},"institutions":[{"id":"https://openalex.org/I58918642","display_name":"Sofia University \"St. Kliment Ohridski\"","ror":"https://ror.org/02jv3k292","country_code":"BG","type":"education","lineage":["https://openalex.org/I58918642"]}],"countries":["BG"],"is_corresponding":true,"raw_author_name":"Angel Beshirov","raw_affiliation_strings":["FMI, Sofia University \u201cSt. Kliment Ohridski\u201d, Sofia, Bulgaria","FMI, Sofia University \"St. Kliment Ohridski\", Sofia, Bulgaria"],"raw_orcid":"https://orcid.org/0000-0002-0684-2730","affiliations":[{"raw_affiliation_string":"FMI, Sofia University \u201cSt. Kliment Ohridski\u201d, Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]},{"raw_affiliation_string":"FMI, Sofia University \"St. Kliment Ohridski\", Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041444516","display_name":"Milena Dobreva","orcid":"https://orcid.org/0000-0002-2579-7541"},"institutions":[{"id":"https://openalex.org/I58918642","display_name":"Sofia University \"St. Kliment Ohridski\"","ror":"https://ror.org/02jv3k292","country_code":"BG","type":"education","lineage":["https://openalex.org/I58918642"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Milena Dobreva","raw_affiliation_strings":["FMI, Sofia University \u201cSt. Kliment Ohridski\u201d, Sofia, Bulgaria","FMI, Sofia University \"St. Kliment Ohridski\", Sofia, Bulgaria"],"raw_orcid":"https://orcid.org/0000-0002-2579-7541","affiliations":[{"raw_affiliation_string":"FMI, Sofia University \u201cSt. Kliment Ohridski\u201d, Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]},{"raw_affiliation_string":"FMI, Sofia University \"St. Kliment Ohridski\", Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101638427","display_name":"Dimitar Dimitrov","orcid":"https://orcid.org/0000-0003-1308-180X"},"institutions":[{"id":"https://openalex.org/I58918642","display_name":"Sofia University \"St. Kliment Ohridski\"","ror":"https://ror.org/02jv3k292","country_code":"BG","type":"education","lineage":["https://openalex.org/I58918642"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Dimitar Dimitrov","raw_affiliation_strings":["FMI, Sofia University \u201cSt. Kliment Ohridski\u201d, Sofia, Bulgaria","FMI, Sofia University \"St. Kliment Ohridski\", Sofia, Bulgaria"],"raw_orcid":"https://orcid.org/0000-0003-1308-180X","affiliations":[{"raw_affiliation_string":"FMI, Sofia University \u201cSt. Kliment Ohridski\u201d, Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]},{"raw_affiliation_string":"FMI, Sofia University \"St. Kliment Ohridski\", Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076120409","display_name":"Momchil Hardalov","orcid":"https://orcid.org/0000-0001-8095-3570"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Momchil Hardalov","raw_affiliation_strings":["AWS AI Labs, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0001-8095-3570","affiliations":[{"raw_affiliation_string":"AWS AI Labs, Barcelona, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076908482","display_name":"Ivan Koychev","orcid":"https://orcid.org/0000-0003-3919-030X"},"institutions":[{"id":"https://openalex.org/I58918642","display_name":"Sofia University \"St. Kliment Ohridski\"","ror":"https://ror.org/02jv3k292","country_code":"BG","type":"education","lineage":["https://openalex.org/I58918642"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Ivan Koychev","raw_affiliation_strings":["FMI, Sofia University \u201cSt. Kliment Ohridski\u201d, Sofia, Bulgaria","FMI, Sofia University \"St. Kliment Ohridski\", Sofia, Bulgaria"],"raw_orcid":"https://orcid.org/0000-0003-3919-030X","affiliations":[{"raw_affiliation_string":"FMI, Sofia University \u201cSt. Kliment Ohridski\u201d, Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]},{"raw_affiliation_string":"FMI, Sofia University \"St. Kliment Ohridski\", Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012055259","display_name":"Preslav Nakov","orcid":"https://orcid.org/0000-0002-3600-1510"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Preslav Nakov","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0002-3600-1510","affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5052702364"],"corresponding_institution_ids":["https://openalex.org/I58918642"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":8.6559,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97084374,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"26","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9883999824523926,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.972599983215332,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/computer-science","display_name":"Computer science","score":0.8438577651977539},{"id":"https://openalex.org/keywords/bulgarian","display_name":"Bulgarian","score":0.81597501039505},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6450908184051514},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5266841650009155},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4260442852973938},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12576138973236084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8438577651977539},{"id":"https://openalex.org/C2780343019","wikidata":"https://www.wikidata.org/wiki/Q7918","display_name":"Bulgarian","level":2,"score":0.81597501039505},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6450908184051514},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5266841650009155},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4260442852973938},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12576138973236084},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00799-025-00415-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00799-025-00415-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00799-025-00415-x.pdf","source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00799-025-00415-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00799-025-00415-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00799-025-00415-x.pdf","source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407832567.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W104170146","https://openalex.org/W1647671624","https://openalex.org/W2011084371","https://openalex.org/W2053276657","https://openalex.org/W2064675550","https://openalex.org/W2100716182","https://openalex.org/W2150429754","https://openalex.org/W2786672397","https://openalex.org/W2798485145","https://openalex.org/W2805283370","https://openalex.org/W2962784628","https://openalex.org/W2963626623","https://openalex.org/W2963979492","https://openalex.org/W2968567788","https://openalex.org/W2979826702","https://openalex.org/W3034797320","https://openalex.org/W3035390927","https://openalex.org/W3046591412","https://openalex.org/W3106274667","https://openalex.org/W4230872509","https://openalex.org/W4237342689","https://openalex.org/W4297803922","https://openalex.org/W4312290170"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4406164758","https://openalex.org/W2419357761","https://openalex.org/W2400831526","https://openalex.org/W1967857157","https://openalex.org/W1563422521","https://openalex.org/W2414976889","https://openalex.org/W4393207791"],"abstract_inverted_index":{"Abstract":[0],"The":[1,176],"digitization":[2],"of":[3,13,145,190,199],"historical":[4,57,103],"documents":[5,105,192],"is":[6,22,43,64,196],"crucial":[7],"for":[8,96,102,125],"preserving":[9],"the":[10,14,74,92,98,108,113,117,137,172,180,184,188,191,203,206],"cultural":[11],"heritage":[12],"society.":[15],"An":[16],"essential":[17],"step":[18,72],"in":[19,107,130,136],"this":[20,42,83,131],"process":[21],"converting":[23],"scanned":[24],"images":[25],"to":[26,54,66,170,202],"text":[27,70,100,174],"using":[28],"Optical":[29],"Character":[30],"Recognition":[31],"(OCR),":[32],"which":[33,158,195],"can":[34],"enable":[35],"further":[36,121],"search,":[37],"information":[38],"extraction,":[39],"etc.":[40],"Unfortunately,":[41],"a":[44,123],"challenging":[45,60],"problem":[46],"as":[47,133,135],"standard":[48,65],"OCR":[49,75,99],"tools":[50],"are":[51],"not":[52],"tailored":[53],"deal":[55],"with":[56,79,161],"orthography":[58,115],"or":[59],"layouts.":[61],"Thus,":[62],"it":[63],"apply":[67],"an":[68,197],"additional":[69],"correction":[71,101],"on":[73,87,205],"output":[76],"when":[77],"dealing":[78],"such":[80],"documents.":[81],"In":[82],"work,":[84],"we":[85,90,159],"focus":[86],"Bulgarian,":[88],"and":[89,155,165,167,215],"create":[91],"first":[93,109],"benchmark":[94],"dataset":[95],"evaluating":[97],"Bulgarian":[104,111,148,209],"written":[106],"standardized":[110],"orthography:":[112],"Drinov":[114],"from":[116],"19th":[118],"century.":[119],"We":[120,150,211],"develop":[122],"method":[124,178],"automatically":[126],"generating":[127],"synthetic":[128],"data":[129,214],"orthography,":[132,140],"well":[134],"subsequent":[138],"Ivanchev":[139],"by":[141,193],"leveraging":[142],"vast":[143],"amounts":[144],"contemporary":[146],"literature":[147],"texts.":[149],"then":[151],"use":[152],"state-of-the-art":[153,204],"LLMs":[154],"encoder-decoder":[156],"framework":[157],"augment":[160],"diagonal":[162],"attention":[163],"loss":[164],"copy":[166],"coverage":[168],"mechanisms":[169],"improve":[171],"post-OCR":[173],"correction.":[175],"proposed":[177],"reduces":[179],"errors":[181],"introduced":[182],"during":[183],"recognition.":[185],"It":[186],"improves":[187],"quality":[189],"25%,":[194],"increase":[198],"16%":[200],"compared":[201],"ICDAR":[207],"2019":[208],"dataset.":[210],"release":[212],"our":[213],"code":[216],"at":[217],"https://github.com/angelbeshirov/post-ocr-text-correction":[218],".":[219]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}
