{"id":"https://openalex.org/W2100716182","doi":"https://doi.org/10.1109/icdar.2003.1227833","title":"Lexical postcorrection of OCR-results:the web as a dynamic secondary dictionary?","display_name":"Lexical postcorrection of OCR-results:the web as a dynamic secondary dictionary?","publication_year":2005,"publication_date":"2005-04-12","ids":{"openalex":"https://openalex.org/W2100716182","doi":"https://doi.org/10.1109/icdar.2003.1227833","mag":"2100716182"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2003.1227833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2003.1227833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","raw_type":"proceedings-article"},"type":"conference-paper","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/A5050863789","display_name":"Christian M. Strohmaier","orcid":null},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"C.M. Strohmaier","raw_affiliation_strings":["University of T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110248832","display_name":"Christoph Ringlstetter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"C. Ringlstetter","raw_affiliation_strings":["CIS, University of Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIS, University of Munich, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109699155","display_name":"Klaus U. Schulz","orcid":null},"institutions":[{"id":"https://openalex.org/I24768866","display_name":"Bulgarian Academy of Sciences","ror":"https://ror.org/01x8hew03","country_code":"BG","type":"government","lineage":["https://openalex.org/I24768866"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"K.U. Schulz","raw_affiliation_strings":["Bulgarian Academy of Sciences, Bulgaria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bulgarian Academy of Sciences, Bulgaria","institution_ids":["https://openalex.org/I24768866"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114255303","display_name":"Stoyan Mihov","orcid":null},"institutions":[{"id":"https://openalex.org/I24768866","display_name":"Bulgarian Academy of Sciences","ror":"https://ror.org/01x8hew03","country_code":"BG","type":"government","lineage":["https://openalex.org/I24768866"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"S. Mihov","raw_affiliation_strings":["Bulgarian Academy of Sciences, Bulgaria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bulgarian Academy of Sciences, Bulgaria","institution_ids":["https://openalex.org/I24768866"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9716,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.87280394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"1133","last_page":"1137"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9866999983787537,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9797000288963318,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8117207884788513},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7502238750457764},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.679857611656189},{"id":"https://openalex.org/keywords/thematic-map","display_name":"Thematic map","score":0.6567949652671814},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6159039735794067},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5335605144500732},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5002880096435547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4925745129585266},{"id":"https://openalex.org/keywords/word-lists-by-frequency","display_name":"Word lists by frequency","score":0.42836838960647583},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42539194226264954},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4147259294986725},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24295175075531006},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11758548021316528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8117207884788513},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7502238750457764},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.679857611656189},{"id":"https://openalex.org/C93692415","wikidata":"https://www.wikidata.org/wiki/Q1502030","display_name":"Thematic map","level":2,"score":0.6567949652671814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6159039735794067},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5335605144500732},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5002880096435547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4925745129585266},{"id":"https://openalex.org/C175293574","wikidata":"https://www.wikidata.org/wiki/Q697133","display_name":"Word lists by frequency","level":3,"score":0.42836838960647583},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42539194226264954},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4147259294986725},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24295175075531006},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11758548021316528},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icdar.2003.1227833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2003.1227833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.3517","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.3517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.uni-muenchen.de/people/Schulz/Pub/ICDAR03.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.12.3075","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.12.3075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.uni-muenchen.de/publications/icdar5.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.70.3298","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.3298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lml.bas.bg/~stoyan/icdar5.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W27881537","https://openalex.org/W1487429615","https://openalex.org/W1647671624","https://openalex.org/W2010595692","https://openalex.org/W2071003614","https://openalex.org/W2099510384","https://openalex.org/W2141265687","https://openalex.org/W2158699664","https://openalex.org/W4241299755","https://openalex.org/W6636915900"],"related_works":["https://openalex.org/W1997182898","https://openalex.org/W2111466409","https://openalex.org/W2127709934","https://openalex.org/W1588516692","https://openalex.org/W323241333","https://openalex.org/W65596523","https://openalex.org/W2089917660","https://openalex.org/W117922251","https://openalex.org/W1560699798","https://openalex.org/W1970935140"],"abstract_inverted_index":{"Postcorrection":[0],"of":[1,27,64,72,86,94,97,108,123,129,153],"OCR-results":[2],"for":[3,138],"text":[4],"documents":[5],"is":[6],"usually":[7],"based":[8],"on":[9,61],"electronic":[10],"dictionaries.":[11,110],"When":[12],"scanning":[13],"texts":[14],"from":[15,55,100,120],"a":[16,24,62,101,121,144],"specific":[17],"thematic":[18,50,141],"area,":[19],"conventional":[20],"dictionaries":[21,76,88,128],"often":[22],"miss":[23],"considerable":[25],"number":[26],"tokens.":[28],"Furthermore,":[29],"if":[30],"word":[31],"frequencies":[32,39,45],"are":[33],"stored":[34],"with":[35,82],"the":[36,44,48,70,84,95,106,130,136,139,151],"entries,":[37],"these":[38,56],"will":[40],"not":[41],"properly":[42],"reflect":[43],"found":[46],"in":[47,143],"given":[49,102,140],"area.":[51],"Correction":[52],"adequacy":[53],"suffers":[54],"two":[57],"shortcomings.":[58],"We":[59],"report":[60],"series":[63],"experiments":[65],"where":[66],"we":[67],"compare":[68],"(1)":[69],"use":[71,85,107],"fixed,":[73],"static":[74],"largescale":[75],"(including":[77],"proper":[78],"names":[79],"and":[80,104,116,147],"abbreviations)":[81],"(2)":[83],"dynamic":[87,127],"retrieved":[89],"via":[90],"an":[91],"automated":[92],"analysis":[93],"vocabulary":[96],"web":[98],"pages":[99],"domain,":[103],"(3)":[105],"mixed":[109],"Our":[111],"experiments,":[112],"which":[113],"address":[114],"English":[115],"German":[117],"document":[118],"collections":[119],"variety":[122],"fields,":[124],"show":[125],"that":[126],"above":[131],"mentioned":[132],"form":[133],"can":[134],"improve":[135,150],"coverage":[137],"area":[142],"significant":[145],"way":[146],"help":[148],"to":[149],"quality":[152],"lexical":[154],"postcorrection":[155],"methods.":[156],"1.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
