{"id":"https://openalex.org/W7160838518","doi":"https://doi.org/10.1145/3815575","title":"A Framework and Dataset for Contextual Post-OCR Correction","display_name":"A Framework and Dataset for Contextual Post-OCR Correction","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160838518","doi":"https://doi.org/10.1145/3815575"},"language":"en","primary_location":{"id":"doi:10.1145/3815575","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3815575","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3815575","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075569432","display_name":"Abhishek Bhandari","orcid":"https://orcid.org/0000-0001-5193-7213"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhishek Bhandari","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology Jodhpur"],"raw_orcid":"https://orcid.org/0000-0001-5193-7213","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Jodhpur","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025684791","display_name":"Gaurav Harit","orcid":"https://orcid.org/0000-0001-7943-0123"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gaurav Harit","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology Jodhpur"],"raw_orcid":"https://orcid.org/0000-0001-7943-0123","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Jodhpur","institution_ids":["https://openalex.org/I154549908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154549908"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5728218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"6","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9879999756813049,"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":0.9879999756813049,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00139999995008111,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7021999955177307},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.6104000210762024},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5943999886512756},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5817000269889832},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5415999889373779},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.445499986410141},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41260001063346863},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4097999930381775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8546000123023987},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7021999955177307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6536999940872192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6485999822616577},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.6104000210762024},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5943999886512756},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5817000269889832},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5415999889373779},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4097999930381775},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.388700008392334},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.367900013923645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3529999852180481},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3815575","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3815575","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3815575","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3815575","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7050405740737915,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1975020655","https://openalex.org/W2003661734","https://openalex.org/W2115239518","https://openalex.org/W2170639752","https://openalex.org/W2423677913","https://openalex.org/W2610411915","https://openalex.org/W3001434439","https://openalex.org/W3164045210","https://openalex.org/W4379793938","https://openalex.org/W4385567067","https://openalex.org/W4412635139","https://openalex.org/W4412886902","https://openalex.org/W4412945183"],"related_works":[],"abstract_inverted_index":{"Optical":[0],"Character":[1],"Recognition":[2],"(OCR)":[3],"has":[4],"accelerated":[5],"the":[6,56,63,96,119,142,148],"digitization":[7],"of":[8],"printed":[9],"Indic":[10,170],"texts,":[11],"yet":[12],"recognition":[13],"remains":[14],"error-prone":[15],"due":[16],"to":[17,31,101,106,112,124,129,135],"ligatures,":[18],"matras,":[19],"conjuncts,":[20],"orthographic":[21],"variability,":[22],"and":[23,72,110,133,154],"long-range":[24],"grammatical":[25],"dependencies.":[26],"Hence,":[27],"it":[28],"is":[29,80,174],"imperative":[30],"employ":[32],"post-OCR":[33,167],"error-correction":[34],"techniques":[35],"that":[36,49,160],"can":[37],"exploit":[38],"broader":[39],"linguistic":[40],"cues.":[41],"This":[42],"article":[43],"presents":[44],"a":[45,51,74,81,87,162],"context-aware":[46],"correction":[47,60,78,168],"framework":[48],"leverages":[50],"larger":[52,163],"sentence-level":[53],"context":[54,70,164],"around":[55],"erroneous":[57],"span.":[58],"The":[59,172],"model":[61,79,84],"inputs":[62],"OCR-generated":[64],"sentence,":[65,71],"along":[66],"with":[67],"an":[68],"auxiliary":[69],"outputs":[73],"corrected":[75],"sequence.":[76],"Our":[77],"pre-trained":[82],"language":[83],"finetuned":[85],"on":[86],"small,":[88],"supervised":[89],"corpus.":[90],"Experiments":[91],"demonstrate":[92,159],"substantial":[93],"reductions":[94],"in":[95],"character":[97,152],"error":[98,121],"rates":[99,122],"(10.20%":[100],"6.73%":[102],"for":[103,108,114,126,131,137,151,169],"Hindi,":[104,127],"6.10%":[105],"1.39%":[107],"Gujarati,":[109,132],"8.19%":[111],"3.29%":[113],"Marathi)":[115],"as":[116,118],"well":[117],"word":[120],"(28.53%":[123],"14.57%":[125],"20.85%":[128],"4.16%":[130],"24.89%":[134],"8.28%":[136],"Marathi).":[138],"These":[139,157],"results":[140,158],"outperform":[141],"seq2seq":[143],"baselines.":[144],"Error-type":[145],"analysis":[146],"indicates":[147],"largest":[149],"improvements":[150],"confusion":[153],"conjunct/ligature":[155],"errors.":[156],"supplying":[161],"consistently":[165],"improves":[166],"scripts.":[171],"dataset":[173],"publicly":[175],"available":[176],"via":[177],"Hugging":[178],"Face":[179],"at":[180],"https://huggingface.co/datasets/AbhishekBhandari/Indic-post-ocr-correction":[181],".":[182]},"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2026-05-12T00:00:00"}