{"id":"https://openalex.org/W4413757219","doi":"https://doi.org/10.1145/3704268.3748673","title":"A Proposal of Post-OCR Spelling Correction Using Monolingual Byte-level Language Models","display_name":"A Proposal of Post-OCR Spelling Correction Using Monolingual Byte-level Language Models","publication_year":2025,"publication_date":"2025-08-27","ids":{"openalex":"https://openalex.org/W4413757219","doi":"https://doi.org/10.1145/3704268.3748673"},"language":"en","primary_location":{"id":"doi:10.1145/3704268.3748673","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704268.3748673","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3748673","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3748673","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108978974","display_name":"S\u00e1vio Santos de Ara\u00fajo","orcid":"https://orcid.org/0000-0002-4707-6948"},"institutions":[{"id":"https://openalex.org/I71437568","display_name":"Universidade de Pernambuco","ror":"https://ror.org/00gtcbp88","country_code":"BR","type":"education","lineage":["https://openalex.org/I71437568"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"S\u00e1vio Santos de Ara\u00fajo","raw_affiliation_strings":["Universidade de Pernambuco, Garanhuns, PE, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade de Pernambuco, Garanhuns, PE, Brazil","institution_ids":["https://openalex.org/I71437568"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049490188","display_name":"Byron Leite Dantas Bezerra","orcid":"https://orcid.org/0000-0002-8327-9734"},"institutions":[{"id":"https://openalex.org/I71437568","display_name":"Universidade de Pernambuco","ror":"https://ror.org/00gtcbp88","country_code":"BR","type":"education","lineage":["https://openalex.org/I71437568"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Byron Leite Dantas Bezerra","raw_affiliation_strings":["Universidade de Pernambuco, Recife, PE, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade de Pernambuco, Recife, PE, Brazil","institution_ids":["https://openalex.org/I71437568"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050966452","display_name":"Arthur Flor de Sousa Neto","orcid":"https://orcid.org/0000-0002-0522-2150"},"institutions":[{"id":"https://openalex.org/I71437568","display_name":"Universidade de Pernambuco","ror":"https://ror.org/00gtcbp88","country_code":"BR","type":"education","lineage":["https://openalex.org/I71437568"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Arthur Flor de Sousa Neto","raw_affiliation_strings":["Universidade de Pernambuco, Recife, PE, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade de Pernambuco, Recife, PE, Brazil","institution_ids":["https://openalex.org/I71437568"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108978974"],"corresponding_institution_ids":["https://openalex.org/I71437568"],"apc_list":null,"apc_paid":null,"fwci":1.2134,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82838669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9984999895095825,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9897000193595886,"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":[{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.9215776920318604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.817253828048706},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.7566598653793335},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.629652738571167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47678685188293457},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43070146441459656},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37697920203208923},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.32159292697906494},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.28901785612106323}],"concepts":[{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.9215776920318604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817253828048706},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.7566598653793335},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.629652738571167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47678685188293457},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43070146441459656},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37697920203208923},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32159292697906494},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28901785612106323},{"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:10.1145/3704268.3748673","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704268.3748673","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3748673","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3704268.3748673","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704268.3748673","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3748673","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3331681876","display_name":null,"funder_award_id":"CAPES","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G3601516360","display_name":null,"funder_award_id":"Brazil","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G5079005330","display_name":null,"funder_award_id":"support","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G692611148","display_name":null,"funder_award_id":"Brazil","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"}],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413757219.pdf","grobid_xml":"https://content.openalex.org/works/W4413757219.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2066792529","https://openalex.org/W2102443632","https://openalex.org/W2152928267","https://openalex.org/W2164867695","https://openalex.org/W2785820430","https://openalex.org/W2786974559","https://openalex.org/W2946759265","https://openalex.org/W3205202687","https://openalex.org/W4224069281","https://openalex.org/W4387522367","https://openalex.org/W4411119628"],"related_works":["https://openalex.org/W2100947578","https://openalex.org/W2161008081","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W1974418053","https://openalex.org/W2081317458","https://openalex.org/W2021532426"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"a":[3,6,109],"proposal":[4],"for":[5,15],"spelling":[7],"corrector":[8],"using":[9,108],"monolingual":[10,131],"byte-level":[11,119],"language":[12],"models":[13],"(Monobyte)":[14],"the":[16,59,116,126],"post-OCR":[17],"task":[18],"in":[19,66,73,88,105,121],"texts":[20],"produced":[21],"by":[22,93,97],"Handwritten":[23],"Text":[24],"Recognition":[25],"(HTR)":[26],"systems.":[27],"We":[28],"evaluate":[29],"three":[30,48],"Monobyte":[31,61,90],"models,":[32],"based":[33],"on":[34,39],"Google's":[35],"ByT5,":[36],"trained":[37],"separately":[38],"English,":[40],"French,":[41],"and":[42,56,71,84,95,124],"Brazilian":[43],"Portuguese.":[44],"The":[45,99],"experiments":[46],"evaluated":[47],"datasets":[49],"with":[50],"21st":[51],"century":[52],"manuscripts:":[53],"IAM,":[54,60],"RIMES,":[55,79],"BRESSAY.":[57],"In":[58,78],"achieves":[62],"reductions":[63,80],"of":[64,118,128],"2.24%":[65],"character":[67],"error":[68,75],"rate":[69,76],"(CER)":[70,83],"26.37%":[72],"word":[74],"(WER).":[77],"are":[81],"13.48%":[82],"33.34%":[85],"(WER),":[86],"while":[87],"BRESSAY,":[89],"improves":[91],"CER":[92],"12.78%":[94],"WER":[96],"40.62%.":[98],"BRESSAY":[100],"results":[101,103],"surpass":[102],"reported":[104],"previous":[106],"works":[107],"multilingual":[110],"ByT5":[111],"model.":[112],"Our":[113],"findings":[114],"demonstrate":[115],"effectiveness":[117],"tokenization":[120],"noisy":[122],"text":[123],"underscore":[125],"potential":[127],"computationally":[129],"efficient,":[130],"models.":[132],"Code":[133],"is":[134],"availabled":[135],"at":[136],"https://github.com/savi8sant8s/monobyte-spelling-corrector.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}