{"id":"https://openalex.org/W2133058591","doi":"https://doi.org/10.1145/1390749.1390753","title":"Optical character recognition errors and their effects on natural language processing","display_name":"Optical character recognition errors and their effects on natural language processing","publication_year":2008,"publication_date":"2008-07-24","ids":{"openalex":"https://openalex.org/W2133058591","doi":"https://doi.org/10.1145/1390749.1390753","mag":"2133058591"},"language":"en","primary_location":{"id":"doi:10.1145/1390749.1390753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","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/A5088217927","display_name":"Daniel Lopresti","orcid":"https://orcid.org/0000-0003-2129-4223"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel Lopresti","raw_affiliation_strings":["Lehigh University, Bethlehem, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehigh University, Bethlehem, PA","institution_ids":["https://openalex.org/I186143895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5088217927"],"corresponding_institution_ids":["https://openalex.org/I186143895"],"apc_list":null,"apc_paid":null,"fwci":5.876,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.95904701,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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":0.845331072807312},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.8084840774536133},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.7444958090782166},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.701438307762146},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6876322031021118},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6296085119247437},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5879396200180054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5465764999389648},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.537732720375061},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5219021439552307},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5127447843551636},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.45856037735939026},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42788833379745483},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33586397767066956},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18694821000099182},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16555148363113403},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1194114089012146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.845331072807312},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8084840774536133},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.7444958090782166},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.701438307762146},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6876322031021118},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6296085119247437},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5879396200180054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5465764999389648},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.537732720375061},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5219021439552307},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5127447843551636},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.45856037735939026},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42788833379745483},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33586397767066956},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18694821000099182},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16555148363113403},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1194114089012146},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1390749.1390753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.75}],"awards":[{"id":"https://openalex.org/G8104918530","display_name":null,"funder_award_id":"CNS-0430178","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W26027032","https://openalex.org/W140312209","https://openalex.org/W1502086103","https://openalex.org/W1534218608","https://openalex.org/W1970549718","https://openalex.org/W1971336721","https://openalex.org/W1976978162","https://openalex.org/W1977053705","https://openalex.org/W2005446794","https://openalex.org/W2009844948","https://openalex.org/W2011084371","https://openalex.org/W2012022516","https://openalex.org/W2018560257","https://openalex.org/W2025641162","https://openalex.org/W2040068729","https://openalex.org/W2160244865","https://openalex.org/W6601049059"],"related_works":["https://openalex.org/W4386014872","https://openalex.org/W1847536016","https://openalex.org/W4361193986","https://openalex.org/W3149094754","https://openalex.org/W2148703997","https://openalex.org/W4366851046","https://openalex.org/W3185922486","https://openalex.org/W2293063786","https://openalex.org/W2575782020","https://openalex.org/W2911292476"],"abstract_inverted_index":{"Errors":[0,85],"are":[1,90],"unavoidable":[2],"in":[3],"advanced":[4],"computer":[5],"vision":[6],"applications":[7],"such":[8,33],"as":[9,74,94,139],"optical":[10],"character":[11],"recognition,":[12],"and":[13,66,86,92,124],"the":[14,48,54,98,114,119,122,125],"noise":[15],"induced":[16],"by":[17],"these":[18],"errors":[19,52],"presents":[20],"a":[21,40,57,80,106],"serious":[22],"challenge":[23],"to":[24,29,112],"down-stream":[25],"processes":[26],"that":[27,134],"attempt":[28],"make":[30],"use":[31],"of":[32,50,56,109,121,130],"data.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,43],"apply":[39],"new":[41],"paradigm":[42],"have":[44],"proposed":[45],"for":[46],"measuring":[47],"impact":[49,116],"recognition":[51],"on":[53,105,118],"stages":[55],"standard":[58],"text":[59,141],"analysis":[60],"pipeline:":[61],"sentence":[62],"boundary":[63],"detection,":[64],"tokenization,":[65],"part-of-speech":[67],"tagging.":[68],"Our":[69],"methodology":[70],"formulates":[71],"error":[72,123],"classification":[73],"an":[75],"optimization":[76],"problem":[77,129],"solvable":[78],"using":[79],"hierarchical":[81],"dynamic":[82],"programming":[83],"approach.":[84],"their":[87],"cascading":[88],"effects":[89],"isolated":[91],"analyzed":[93],"they":[95],"travel":[96],"through":[97],"pipeline.":[99],"We":[100],"present":[101],"experimental":[102],"results":[103],"based":[104],"large":[107],"collection":[108],"scanned":[110],"pages":[111],"study":[113],"varying":[115],"depending":[117],"nature":[120],"character(s)":[126],"involved.":[127],"The":[128],"identifying":[131],"tabular":[132],"structures":[133],"should":[135],"not":[136],"be":[137],"parsed":[138],"sentential":[140],"is":[142],"also":[143],"discussed.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}