{"id":"https://openalex.org/W4402396664","doi":"https://doi.org/10.1007/978-3-031-70645-5_2","title":"TrOCR Meets Language Models: An End-to-End Post-correction Approach","display_name":"TrOCR Meets Language Models: An End-to-End Post-correction Approach","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402396664","doi":"https://doi.org/10.1007/978-3-031-70645-5_2"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-70645-5_2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-70645-5_2","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-031-70645-5_2","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032447928","display_name":"Y. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Yung-Hsin Chen","raw_affiliation_strings":["Department of Computational Linguistics, University of Zurich, Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Computational Linguistics, University of Zurich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055524248","display_name":"Phillip Str\u00f6bel","orcid":"https://orcid.org/0000-0003-2063-5495"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Phillip B. Str\u00f6bel","raw_affiliation_strings":["Department of Computational Linguistics, University of Zurich, Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Computational Linguistics, University of Zurich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032447928"],"corresponding_institution_ids":["https://openalex.org/I202697423"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":1.5588,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.84226665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9986000061035156,"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":0.9926000237464905,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8387186527252197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8223603963851929},{"id":"https://openalex.org/keywords/end-of-history","display_name":"End of history","score":0.4224895238876343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23386302590370178}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8387186527252197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223603963851929},{"id":"https://openalex.org/C2778935963","wikidata":"https://www.wikidata.org/wiki/Q13218530","display_name":"End of history","level":3,"score":0.4224895238876343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23386302590370178},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-031-70645-5_2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-70645-5_2","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:doi:10.5167/uzh-262170","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-70645-5_2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-70645-5_2","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1993155451","https://openalex.org/W2031094399","https://openalex.org/W2060580591","https://openalex.org/W2519545558","https://openalex.org/W2793614051","https://openalex.org/W2809806860","https://openalex.org/W2810983211","https://openalex.org/W2962784628","https://openalex.org/W2981597140","https://openalex.org/W3004778073","https://openalex.org/W3094502228","https://openalex.org/W3095771422","https://openalex.org/W3107428334","https://openalex.org/W3111885845","https://openalex.org/W3112627564","https://openalex.org/W3168553196","https://openalex.org/W3169197486","https://openalex.org/W3176276424","https://openalex.org/W3178709966","https://openalex.org/W3199662997","https://openalex.org/W3199928321","https://openalex.org/W4312290170","https://openalex.org/W4385819993","https://openalex.org/W6600002382","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W3016188207","https://openalex.org/W3179968364","https://openalex.org/W3118453067","https://openalex.org/W4286908490","https://openalex.org/W4307058106","https://openalex.org/W2964709658","https://openalex.org/W2795393712","https://openalex.org/W4308474082","https://openalex.org/W4393212338","https://openalex.org/W2218833963"],"abstract_inverted_index":{"This":[0,31],"study":[1],"aims":[2],"to":[3,85,121,123],"enhance":[4],"handwritten":[5,146],"text":[6,40],"recognition":[7,18],"(HTR)":[8],"performance":[9],"and":[10,45,61,106],"domain":[11,43],"adaptability":[12],"by":[13,77],"combining":[14],"an":[15],"optical":[16],"character":[17],"(OCR)":[19],"model":[20,24,102,118],"with":[21],"a":[22,29,57,63,140],"language":[23],"(LM)":[25],"that":[26,98],"serves":[27],"as":[28],"corrector.":[30],"integration":[32],"addresses":[33],"three":[34],"principal":[35],"challenges:":[36],"over-correction,":[37],"which":[38],"compromises":[39],"authenticity;":[41],"poor":[42],"adaptation;":[44],"the":[46,53,78,81,99,110,113,117,128,137],"scarcity":[47],"of":[48,69,112,143],"annotated":[49,144],"images.":[50,147],"We":[51],"explore":[52],"synergy":[54],"between":[55],"TrOCR,":[56],"state-of-the-art":[58],"OCR":[59],"model,":[60],"CharBERT,":[62],"BERT-based":[64],"LM.":[65],"A":[66],"novel":[67],"aspect":[68],"our":[70],"research":[71],"involves":[72],"introducing":[73],"common":[74],"errors":[75,88],"made":[76],"recogniser":[79,129],"into":[80],"LM,":[82],"enabling":[83],"it":[84],"consider":[86],"these":[87],"during":[89],"correction,":[90],"thereby":[91],"improving":[92],"overall":[93],"performance.":[94],"Our":[95],"findings":[96],"reveal":[97],"hybrid":[100],"TrOCR-CharBERT":[101],"effectively":[103],"balances":[104],"visual":[105],"linguistic":[107],"information,":[108],"preserving":[109],"authenticity":[111],"original":[114],"texts.":[115],"Furthermore,":[116],"is":[119,130],"able":[120],"adapt":[122],"historical":[124,145],"data":[125],"even":[126],"when":[127],"trained":[131],"solely":[132],"on":[133],"contemporary":[134],"data,":[135],"mitigating":[136],"need":[138],"for":[139],"large":[141],"number":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}