{"id":"https://openalex.org/W4399641285","doi":"https://doi.org/10.1186/s40537-024-00927-4","title":"Advancing machine learning with OCR2SEQ: an innovative approach to multi-modal data augmentation","display_name":"Advancing machine learning with OCR2SEQ: an innovative approach to multi-modal data augmentation","publication_year":2024,"publication_date":"2024-06-13","ids":{"openalex":"https://openalex.org/W4399641285","doi":"https://doi.org/10.1186/s40537-024-00927-4"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-024-00927-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-024-00927-4","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00927-4","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"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":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00927-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033396009","display_name":"Michael R. Lowe","orcid":"https://orcid.org/0000-0002-6301-9214"},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Lowe","raw_affiliation_strings":["Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085551052","display_name":"Joseph D. Prusa","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph D. Prusa","raw_affiliation_strings":["Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004094853","display_name":"Joffrey L. Leevy","orcid":"https://orcid.org/0000-0002-7079-7540"},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joffrey L. Leevy","raw_affiliation_strings":["Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089170562","display_name":"Taghi M. Khoshgoftaar","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taghi M. Khoshgoftaar","raw_affiliation_strings":["Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA","institution_ids":["https://openalex.org/I63772739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033396009"],"corresponding_institution_ids":["https://openalex.org/I63772739"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":0.6731,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68706181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"11","issue":"1","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":0.9991999864578247,"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":0.9991999864578247,"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":0.9904000163078308,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9894000291824341,"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/computer-science","display_name":"Computer science","score":0.8607255220413208},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6333608627319336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5350500345230103},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5181195139884949},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5134128332138062},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4564383924007416},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4429852068424225},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4363534450531006},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43627700209617615},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4185869097709656},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.41852909326553345},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3556900918483734}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8607255220413208},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6333608627319336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5350500345230103},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5181195139884949},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5134128332138062},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4564383924007416},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4429852068424225},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4363534450531006},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43627700209617615},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4185869097709656},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.41852909326553345},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3556900918483734},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s40537-024-00927-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-024-00927-4","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00927-4","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"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":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bcfa728aeb4e41c6a4c2023e9c0de0a9","is_oa":true,"landing_page_url":"https://doaj.org/article/bcfa728aeb4e41c6a4c2023e9c0de0a9","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":"Journal of Big Data, Vol 11, Iss 1, Pp 1-20 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-024-00927-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-024-00927-4","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00927-4","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"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":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399641285.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W109287966","https://openalex.org/W2001642682","https://openalex.org/W2396881363","https://openalex.org/W2505955429","https://openalex.org/W2953342969","https://openalex.org/W2954996726","https://openalex.org/W2972075936","https://openalex.org/W2981852735","https://openalex.org/W3164045210","https://openalex.org/W3176923149","https://openalex.org/W3196199406","https://openalex.org/W4245080148","https://openalex.org/W4286971636","https://openalex.org/W4295939028","https://openalex.org/W4382202677"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W4246352526","https://openalex.org/W2121910908"],"abstract_inverted_index":{"Abstract":[0],"OCR2SEQ":[1,54,94,123],"represents":[2],"an":[3],"innovative":[4],"advancement":[5,147],"in":[6,22,40,99,104,148,153,172],"Optical":[7],"Character":[8],"Recognition":[9],"(OCR)":[10],"technology,":[11,150],"leveraging":[12],"a":[13,56,169],"multi-modal":[14],"generative":[15],"augmentation":[16,60],"strategy":[17],"to":[18,32,63,124],"overcome":[19],"traditional":[20],"limitations":[21],"OCR":[23,109,126,149,180],"systems.":[24],"This":[25,117,146],"paper":[26,118],"introduces":[27],"OCR2SEQ\u2019s":[28],"unique":[29],"approach,":[30],"tailored":[31],"enhance":[33],"data":[34,78,100,164,177],"quality":[35],"for":[36,138,178],"sequence-to-sequence":[37],"models,":[38],"especially":[39],"scenarios":[41],"characterized":[42],"by":[43,128],"sparse":[44],"character":[45],"sets":[46,168],"and":[47,76,86,114,141,161],"specialized":[48],"vocabularies.":[49],"At":[50],"the":[51,83,120,136,154,159,173],"heart":[52],"of":[53,58,88,93,122,163,175],"lies":[55],"set":[57],"novel":[59],"techniques":[61,70],"designed":[62],"simulate":[64],"realistic":[65],"text":[66],"extraction":[67],"errors.":[68],"These":[69],"are":[71],"adept":[72],"at":[73],"generating":[74],"diverse":[75],"challenging":[77],"scenarios,":[79],"thereby":[80],"substantially":[81],"improving":[82],"training":[84],"efficacy":[85],"accuracy":[87,160],"text-to-text":[89],"transformers.":[90],"The":[91],"application":[92],"has":[95],"shown":[96],"notable":[97],"improvements":[98],"processing":[101,165],"accuracy,":[102],"particularly":[103],"sectors":[105],"heavily":[106],"dependent":[107],"on":[108],"technologies":[110],"such":[111],"as":[112,151],"healthcare":[113],"library":[115],"sciences.":[116],"demonstrates":[119],"capability":[121],"transform":[125],"systems":[127],"enriching":[129],"them":[130],"with":[131],"augmented,":[132],"domain-specific":[133],"data,":[134],"paving":[135],"way":[137],"more":[139],"sophisticated":[140],"reliable":[142],"machine":[143],"learning":[144],"interpretations.":[145],"presented":[152],"study,":[155],"not":[156],"only":[157],"enhances":[158],"reliability":[162],"but":[166],"also":[167],"new":[170],"benchmark":[171],"integration":[174],"augmented":[176],"refining":[179],"capabilities.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}