{"id":"https://openalex.org/W4415421551","doi":"https://doi.org/10.15439/2025f1103","title":"Treating OCR Output as a Language (TOOL) \u2013 Improving OCR Output with Seq2Seq Translation","display_name":"Treating OCR Output as a Language (TOOL) \u2013 Improving OCR Output with Seq2Seq Translation","publication_year":2025,"publication_date":"2025-10-15","ids":{"openalex":"https://openalex.org/W4415421551","doi":"https://doi.org/10.15439/2025f1103"},"language":"en","primary_location":{"id":"doi:10.15439/2025f1103","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2025f1103","pdf_url":"https://annals-csis.org/Volume_43/drp/pdf/1103.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://annals-csis.org/Volume_43/drp/pdf/1103.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114602196","display_name":"Thomas Asselborn","orcid":"https://orcid.org/0009-0005-3011-7626"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Asselborn","raw_affiliation_strings":["University of Hamburg"],"raw_orcid":"https://orcid.org/0009-0005-3011-7626","affiliations":[{"raw_affiliation_string":"University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041489447","display_name":"Magnus Bender","orcid":"https://orcid.org/0000-0002-1854-225X"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Magnus Bender","raw_affiliation_strings":["Aarhus University"],"raw_orcid":"https://orcid.org/0000-0002-1854-225X","affiliations":[{"raw_affiliation_string":"Aarhus University","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101970015","display_name":"Ralf M\u00f6ller","orcid":"https://orcid.org/0000-0002-1174-3323"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf M\u00f6ller","raw_affiliation_strings":["University of Hamburg"],"raw_orcid":"https://orcid.org/0000-0002-1174-3323","affiliations":[{"raw_affiliation_string":"University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086948959","display_name":"Sylvia Melzer","orcid":"https://orcid.org/0000-0002-0144-5429"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sylvia Melzer","raw_affiliation_strings":["University of Hamburg"],"raw_orcid":"https://orcid.org/0000-0002-0144-5429","affiliations":[{"raw_affiliation_string":"University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2448395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"43","issue":null,"first_page":"471","last_page":"478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9718999862670898,"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/T10028","display_name":"Topic Modeling","score":0.9578999876976013,"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/optical-character-recognition","display_name":"Optical character recognition","score":0.7250999808311462},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6118999719619751},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5612999796867371},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5131000280380249},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.47920000553131104},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4587000012397766},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.4350000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8087000250816345},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7250999808311462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6524999737739563},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6118999719619751},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6043000221252441},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5612999796867371},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5335000157356262},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5131000280380249},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.3463999927043915},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.15439/2025f1103","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2025f1103","pdf_url":"https://annals-csis.org/Volume_43/drp/pdf/1103.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/c091dbc3-d319-4ee6-9e6d-09debc20245c","is_oa":true,"landing_page_url":"https://pure.au.dk/portal/en/publications/c091dbc3-d319-4ee6-9e6d-09debc20245c","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:doaj.org/article:ad6c4e936ae741f3bc2000dd1d267204","is_oa":true,"landing_page_url":"https://doaj.org/article/ad6c4e936ae741f3bc2000dd1d267204","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Annals of computer science and information systems, Vol 43, Pp 471-478 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.15439/2025f1103","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2025f1103","pdf_url":"https://annals-csis.org/Volume_43/drp/pdf/1103.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415421551.pdf","grobid_xml":"https://content.openalex.org/works/W4415421551.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1560859358","https://openalex.org/W2001642682","https://openalex.org/W2101105183","https://openalex.org/W2143017621","https://openalex.org/W2964343359","https://openalex.org/W3034999214","https://openalex.org/W3039695075","https://openalex.org/W4213413501","https://openalex.org/W4380364384","https://openalex.org/W4399747759","https://openalex.org/W4404261956"],"related_works":[],"abstract_inverted_index":{"Optical":[0],"Character":[1],"Recognition":[2],"(OCR)":[3],"systems":[4],"are":[5],"frequently":[6],"used":[7],"to":[8,69,89,95],"digitise":[9],"text,":[10],"but":[11],"often":[12],"produce":[13],"noisy":[14,53],"results,":[15],"especially":[16],"with":[17],"historical,":[18],"poor-quality":[19],"or":[20],"multilingual":[21],"data.Despite":[22],"advances":[23],"in":[24,59],"OCR":[25,35,45,54,111],"technology,":[26],"post-processing":[27],"remains":[28],"a":[29,38,40,48,57],"significant":[30],"bottleneck.We":[31],"propose":[32],"TOOL":[33,63],"(Treating":[34],"Output":[36],"as":[37,47,56],"Language),":[39],"new":[41],"approach":[42,84],"that":[43],"understands":[44],"correction":[46],"machine":[49],"translation":[50],"task.By":[51],"treating":[52],"text":[55],"language":[58],"its":[60],"own":[61],"right,":[62],"employs":[64],"sequenceto-sequence":[65],"models":[66],"like":[67],"Marian":[68],"translate":[70],"it":[71],"into":[72],"clean,":[73],"standardised":[74],"text.This":[75],"method":[76],"is":[77],"scalable,":[78],"model-independent":[79],"and":[80,113],"language-flexible.We":[81],"demonstrate":[82],"this":[83],"by":[85,105],"translating":[86],"\"OCR":[87],"German\"":[88],"Standard":[90],"German":[91],"from":[92],"around":[93],"1871":[94],"the":[96,102],"present":[97],"day,":[98],"improving":[99],"accuracy":[100],"at":[101],"token":[103],"level":[104],"using":[106],"matched":[107],"training":[108],"pairs":[109],"of":[110],"output":[112],"base":[114],"text.":[115]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-24T00:00:00"}
