{"id":"https://openalex.org/W2007484634","doi":"https://doi.org/10.1145/1568296.1568317","title":"Effect of OCR-errors on the transformation of semi-structured text data into relational database","display_name":"Effect of OCR-errors on the transformation of semi-structured text data into relational database","publication_year":2009,"publication_date":"2009-07-23","ids":{"openalex":"https://openalex.org/W2007484634","doi":"https://doi.org/10.1145/1568296.1568317","mag":"2007484634"},"language":"en","primary_location":{"id":"doi:10.1145/1568296.1568317","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1568296.1568317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third 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/A5062787733","display_name":"Kolyo Onkov","orcid":"https://orcid.org/0000-0001-7549-0938"},"institutions":[{"id":"https://openalex.org/I4210144807","display_name":"Agricultural University Plovdiv","ror":"https://ror.org/04e5bwf87","country_code":"BG","type":"education","lineage":["https://openalex.org/I4210144807"]}],"countries":["BG"],"is_corresponding":true,"raw_author_name":"Kolyo Z. Onkov","raw_affiliation_strings":["Agricultural University, Plovdiv, Bulgaria"],"affiliations":[{"raw_affiliation_string":"Agricultural University, Plovdiv, Bulgaria","institution_ids":["https://openalex.org/I4210144807"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5062787733"],"corresponding_institution_ids":["https://openalex.org/I4210144807"],"apc_list":null,"apc_paid":null,"fwci":0.38114844,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76271943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9944000244140625,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9944000244140625,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9793000221252441,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.972599983215332,"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":0.7627438306808472},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6781629323959351},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.6200371980667114},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6050483584403992},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5902965664863586},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.5597639083862305},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5381708145141602},{"id":"https://openalex.org/keywords/bulgarian","display_name":"Bulgarian","score":0.46175599098205566},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.4373651146888733},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4259204864501953},{"id":"https://openalex.org/keywords/relational-model","display_name":"Relational model","score":0.4172299802303314},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36118870973587036},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32915857434272766},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10354447364807129},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0977432131767273},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.08677533268928528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7627438306808472},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6781629323959351},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.6200371980667114},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6050483584403992},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5902965664863586},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.5597639083862305},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5381708145141602},{"id":"https://openalex.org/C2780343019","wikidata":"https://www.wikidata.org/wiki/Q7918","display_name":"Bulgarian","level":2,"score":0.46175599098205566},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.4373651146888733},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4259204864501953},{"id":"https://openalex.org/C40207289","wikidata":"https://www.wikidata.org/wiki/Q755662","display_name":"Relational model","level":3,"score":0.4172299802303314},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36118870973587036},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32915857434272766},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10354447364807129},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0977432131767273},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.08677533268928528},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1568296.1568317","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1568296.1568317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Workshop on Analytics for Noisy Unstructured Text Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1535992660","https://openalex.org/W1604803281","https://openalex.org/W2015991179","https://openalex.org/W2133058591","https://openalex.org/W2294792814","https://openalex.org/W3119603699","https://openalex.org/W4301005547"],"related_works":["https://openalex.org/W2267077731","https://openalex.org/W2386578196","https://openalex.org/W3091612633","https://openalex.org/W2483382562","https://openalex.org/W2085988990","https://openalex.org/W1528519853","https://openalex.org/W1510134535","https://openalex.org/W2376710457","https://openalex.org/W1897774768","https://openalex.org/W3006903421"],"abstract_inverted_index":{"Paper":[0],"guides":[1],"and":[2,11,32,34,84,114],"reference":[3,95],"books":[4],"in":[5,17,86,107],"the":[6,18,28,45,60,80,87,108,111,120,123],"fields":[7],"of":[8,20,30,39,54,89,91,110,122],"Pharmacology,":[9],"Veterinary":[10],"Crops":[12],"Protection":[13],"are":[14,38],"often":[15],"presented":[16],"form":[19,109],"semi-structured":[21,68],"text":[22,69],"data.":[23],"\"Key":[24],"words\",":[25],"for":[26,43],"instance,":[27],"names":[29],"diseases":[31],"drugs,":[33],"relationships":[35,55],"between":[36],"them":[37],"a":[40],"great":[41],"importance":[42],"obtaining":[44],"useful":[46],"information":[47],"--":[48],"advice,":[49],"instructions,":[50],"etc.":[51],"The":[52,76],"definition":[53],"is":[56,62],"significant":[57],"problem":[58],"when":[59],"aim":[61],"to":[63,104],"transform":[64],"relatively":[65],"big":[66],"amount":[67],"data":[70,112,124],"into":[71,97],"intelligent":[72],"computer":[73],"based":[74],"system.":[75],"paper":[77],"shortly":[78],"presents":[79],"OCR":[81],"errors":[82],"detection":[83],"correction":[85],"process":[88],"transformation":[90],"Bulgarian":[92],"crops":[93],"protection":[94],"book":[96],"relational":[98],"database.":[99],"Finally,":[100],"this":[101],"solution":[102],"leads":[103],"substantial":[105],"change":[106,119],"presentation":[113],"access.":[115],"This":[116],"does":[117],"not":[118],"essence":[121],"itself.":[125]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
