{"id":"https://openalex.org/W2081366726","doi":"https://doi.org/10.1109/icdar.2007.4377099","title":"Context-Sensitive Error Correction: Using Topic Models to Improve OCR","display_name":"Context-Sensitive Error Correction: Using Topic Models to Improve OCR","publication_year":2007,"publication_date":"2007-09-01","ids":{"openalex":"https://openalex.org/W2081366726","doi":"https://doi.org/10.1109/icdar.2007.4377099","mag":"2081366726"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2007.4377099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4377099","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016675333","display_name":"Michael J. Wick","orcid":"https://orcid.org/0000-0001-5683-8687"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M. Wick","raw_affiliation_strings":["Computer Science and Psychology Departments, University of Massachusetts, Amherst, Amherst, MA, USA","University of Massachusetts Amherst, Amherst#TAB#"],"affiliations":[{"raw_affiliation_string":"Computer Science and Psychology Departments, University of Massachusetts, Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101917153","display_name":"Miriam Ross","orcid":"https://orcid.org/0000-0003-3932-6617"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Ross","raw_affiliation_strings":["Computer Science and Psychology Departments, University of Massachusetts, Amherst, Amherst, MA, USA","University of Massachusetts Amherst, Amherst#TAB#"],"affiliations":[{"raw_affiliation_string":"Computer Science and Psychology Departments, University of Massachusetts, Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045674062","display_name":"Erik Learned-Miller","orcid":"https://orcid.org/0000-0002-3778-9135"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E. Learned-Miller","raw_affiliation_strings":["Computer Science and Psychology Departments, University of Massachusetts, Amherst, Amherst, MA, USA","University of Massachusetts Amherst, Amherst#TAB#"],"affiliations":[{"raw_affiliation_string":"Computer Science and Psychology Departments, University of Massachusetts, Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016675333"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":2.6976,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.89275362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"3","issue":null,"first_page":"1168","last_page":"1172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9926999807357788,"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":0.9916999936103821,"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":0.878509521484375},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7469242811203003},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6675033569335938},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6663589477539062},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6606375575065613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6479974985122681},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6315616369247437},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.588578999042511},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5172751545906067},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5067837834358215},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5066710114479065},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.493163526058197},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4216195046901703},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4117637574672699},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.358900785446167},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10588407516479492},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09241318702697754},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08864811062812805},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07001292705535889}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.878509521484375},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7469242811203003},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6675033569335938},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6663589477539062},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6606375575065613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6479974985122681},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6315616369247437},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.588578999042511},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5172751545906067},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5067837834358215},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5066710114479065},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.493163526058197},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4216195046901703},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4117637574672699},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.358900785446167},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10588407516479492},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09241318702697754},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08864811062812805},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07001292705535889},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icdar.2007.4377099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4377099","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarworks.umass.edu:cs_faculty_pubs-1738","is_oa":false,"landing_page_url":"https://scholarworks.umass.edu/cs_faculty_pubs/739","pdf_url":null,"source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department Faculty Publication Series","raw_type":"text"},{"id":"pmh:oai:scholarworks.umass.edu:20.500.14394/10341","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.14394/10341","pdf_url":null,"source":{"id":"https://openalex.org/S4306402057","display_name":"Scholarworks (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"published","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320311089","display_name":"National Security Agency","ror":"https://ror.org/0047bvr32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W1915058860","https://openalex.org/W2042980227","https://openalex.org/W2100716182","https://openalex.org/W2132827946","https://openalex.org/W2137857605","https://openalex.org/W2144872023","https://openalex.org/W2161074727","https://openalex.org/W2334889010","https://openalex.org/W4231510805","https://openalex.org/W6639619044","https://openalex.org/W6639973174","https://openalex.org/W6680397727"],"related_works":["https://openalex.org/W2292997772","https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2575782020","https://openalex.org/W68335373","https://openalex.org/W4385890381","https://openalex.org/W2402231715"],"abstract_inverted_index":{"Modern":[0],"optical,":[1],"character":[2],"recognition":[3],"software":[4,17],"relies":[5],"on":[6],"human":[7],"interaction":[8],"to":[9,32],"correct":[10,34],"mis":[11],"recognized":[12],"characters.":[13],"Even":[14],"though":[15],"the":[16,23],"often":[18],"reliably":[19],"identifies":[20],"low-confidence":[21],"output,":[22],"simple":[24],"language":[25],"and":[26,45,67],"vocabulary":[27],"models":[28],"employed":[29],"are":[30],"insufficient":[31],"automatically":[33,43],"mistakes.":[35],"This":[36],"paper":[37],"demonstrates":[38],"that":[39],"topic":[40],"models,":[41],"which":[42],"detect":[44],"represent":[46],"an":[47,74],"article's":[48],"semantic":[49],"context,":[50],"reduces":[51],"error":[52],"by":[53],"7%":[54],"over":[55],"a":[56,61],"global":[57],"word":[58],"distribution":[59],"in":[60,70],"simulated":[62],"OCR":[63],"correction":[64],"task.":[65],"Detecting":[66],"leveraging":[68],"context":[69],"this":[71],"manner":[72],"is":[73],"important":[75],"step":[76],"towards":[77],"improving":[78],"OCR.":[79]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}