{"id":"https://openalex.org/W4403488197","doi":"https://doi.org/10.3233/faia240577","title":"Synthetically Augmented Self-Supervised Fine-Tuning for Diverse Text OCR Correction","display_name":"Synthetically Augmented Self-Supervised Fine-Tuning for Diverse Text OCR Correction","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403488197","doi":"https://doi.org/10.3233/faia240577"},"language":"en","primary_location":{"id":"doi:10.3233/faia240577","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240577","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia240577","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102684501","display_name":"Shuhao Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Shuhao Guan","raw_affiliation_strings":["Insight Centre for Data Analytics, Dublin School of Computer Science, University College Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insight Centre for Data Analytics, Dublin School of Computer Science, University College Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053619267","display_name":"Derek Greene","orcid":"https://orcid.org/0000-0001-8065-5418"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Derek Greene","raw_affiliation_strings":["Insight Centre for Data Analytics, Dublin School of Computer Science, University College Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insight Centre for Data Analytics, Dublin School of Computer Science, University College Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I100930933"],"apc_list":null,"apc_paid":null,"fwci":0.3584,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68784159,"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":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":0.9599000215530396,"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":0.9599000215530396,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9409999847412109,"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/computer-science","display_name":"Computer science","score":0.5750504732131958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.543026328086853},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42996689677238464},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34242743253707886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5750504732131958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.543026328086853},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42996689677238464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34242743253707886}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia240577","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240577","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia240577","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240577","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"adoption":[1],"of":[2,15,112],"Optical":[3],"Character":[4],"Recognition":[5],"(OCR)":[6],"tools":[7],"has":[8],"been":[9],"central":[10],"to":[11,50,73,95,100],"the":[12,19,55,110,113],"increased":[13],"digitization":[14],"historical":[16],"documents.":[17],"However,":[18],"errors":[20,70],"introduced":[21],"during":[22],"OCR,":[23],"particularly":[24],"in":[25],"texts":[26],"with":[27],"a":[28,40,88],"specialized":[29],"vocabulary":[30],"(SV),":[31],"necessitate":[32],"effective":[33],"post-OCR":[34,52,83,117],"correction":[35,53],"methodologies.":[36],"This":[37],"study":[38],"introduces":[39],"novel":[41],"approach":[42],"that":[43],"leverages":[44],"weak":[45],"supervision":[46],"and":[47,71,105],"self-supervised":[48,90],"fine-tuning":[49,91],"enhance":[51],"without":[54],"need":[56],"for":[57,82],"substantial":[58],"manual":[59],"annotations.":[60],"By":[61],"using":[62],"multi-noise-level":[63],"synthetic":[64],"data,":[65],"generated":[66],"through":[67],"automatically-extracted":[68],"OCR":[69],"applied":[72,93],"clean":[74],"texts,":[75,97],"we":[76,86,108],"can":[77],"train":[78],"robust":[79],"models":[80,99],"tailored":[81],"tasks.":[84,118],"Furthermore,":[85],"propose":[87],"unique":[89],"strategy,":[92],"specifically":[94],"long":[96],"enables":[98],"adeptly":[101],"handle":[102],"out-of-vocabulary":[103],"problems":[104],"SV.":[106],"Additionally,":[107],"tested":[109],"performance":[111],"GPT":[114],"model":[115],"on":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}