{"id":"https://openalex.org/W2131930823","doi":"https://doi.org/10.1109/icsmc.2004.1401278","title":"A Chinese OCR spelling check approach based on statistical language models","display_name":"A Chinese OCR spelling check approach based on statistical language models","publication_year":2005,"publication_date":"2005-04-06","ids":{"openalex":"https://openalex.org/W2131930823","doi":"https://doi.org/10.1109/icsmc.2004.1401278","mag":"2131930823"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2004.1401278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2004.1401278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)","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/A5115076694","display_name":"Zhuang Li","orcid":"https://orcid.org/0009-0006-3870-4275"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhuang","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111562712","display_name":"Ta Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ta Bao","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xioyan Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xioyan Zhu","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041494720","display_name":"Chunheng Wang","orcid":"https://orcid.org/0000-0002-9589-8284"},"institutions":[{"id":"https://openalex.org/I4210159607","display_name":"Fujitsu (China)","ror":"https://ror.org/04w4yzw62","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159607"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunheng Wang","raw_affiliation_strings":["Fujitsu Research and Development Center Company Limited, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research and Development Center Company Limited, Beijing, China","institution_ids":["https://openalex.org/I4210159607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031845777","display_name":"Satoshi Naoi","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Naoi","raw_affiliation_strings":["Fujitsu Laboratories Limited, Kawasaki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Laboratories Limited, Kawasaki, Japan","institution_ids":["https://openalex.org/I2252096349"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2972,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.89880112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"5","issue":null,"first_page":"4727","last_page":"4732"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9980000257492065,"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":0.9973999857902527,"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":0.8721965551376343},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.7437971234321594},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7358543276786804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6879619359970093},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6554542779922485},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5394533276557922},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.5340166687965393},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.5286890864372253},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.48404234647750854},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4812588393688202},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4574607312679291},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3235136568546295},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18060585856437683},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13803833723068237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8721965551376343},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.7437971234321594},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7358543276786804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6879619359970093},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6554542779922485},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5394533276557922},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.5340166687965393},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.5286890864372253},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.48404234647750854},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4812588393688202},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4574607312679291},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3235136568546295},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18060585856437683},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13803833723068237},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icsmc.2004.1401278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2004.1401278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.114.9032","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.114.9032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csai.tsinghua.edu.cn/~zxy/paper/200410221626172714175e-02.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W99399284","https://openalex.org/W166966826","https://openalex.org/W174914767","https://openalex.org/W1992300521","https://openalex.org/W2071606880","https://openalex.org/W2072773380","https://openalex.org/W2080018251","https://openalex.org/W2105638720","https://openalex.org/W2118714763","https://openalex.org/W2119907552","https://openalex.org/W2119966617","https://openalex.org/W2147152072","https://openalex.org/W2204274716","https://openalex.org/W6604065652","https://openalex.org/W6606753143","https://openalex.org/W6607118547"],"related_works":["https://openalex.org/W2250909759","https://openalex.org/W2532616038","https://openalex.org/W2787311093","https://openalex.org/W2057384730","https://openalex.org/W4307474317","https://openalex.org/W2147879411","https://openalex.org/W2624072012","https://openalex.org/W2008468404","https://openalex.org/W2132221452","https://openalex.org/W2081295016"],"abstract_inverted_index":{"This":[0,19],"work":[1],"describes":[2],"an":[3],"effective":[4],"spelling":[5],"check":[6],"approach":[7],"for":[8],"Chinese":[9,49],"OCR":[10],"with":[11],"a":[12],"new":[13,30],"multi-knowledge":[14],"based":[15],"statistical":[16],"language":[17,20,26,35],"model.":[18],"model":[21,27],"combines":[22],"the":[23,29,60,74],"conventional":[24],"n-gram":[25],"and":[28,42],"LSA":[31],"(latent":[32],"semantic":[33],"analysis)":[34],"model,":[36],"so":[37],"both":[38],"local":[39],"information":[40,44],"(syntax)":[41],"global":[43],"(semantic)":[45],"are":[46,52],"utilized.":[47],"Furthermore,":[48],"similar":[50],"characters":[51],"used":[53],"in":[54,63],"Viterbi":[55],"search":[56],"process":[57],"to":[58,65,82],"expand":[59],"candidate":[61],"list":[62],"order":[64],"add":[66],"more":[67],"possible":[68],"correct":[69],"results.":[70],"With":[71],"our":[72],"approach,":[73],"best":[75],"recognition":[76],"accuracy":[77],"rate":[78],"increases":[79],"from":[80],"79.3%":[81],"91.9%,":[83],"which":[84],"means":[85],"60.9%":[86],"error":[87],"reduction.":[88]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}