{"id":"https://openalex.org/W3131791668","doi":"https://doi.org/10.1515/comp-2020-0143","title":"Diacritics restoration based on word n-grams for Slovak texts","display_name":"Diacritics restoration based on word n-grams for Slovak texts","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3131791668","doi":"https://doi.org/10.1515/comp-2020-0143","mag":"3131791668"},"language":"en","primary_location":{"id":"doi:10.1515/comp-2020-0143","is_oa":true,"landing_page_url":"https://doi.org/10.1515/comp-2020-0143","pdf_url":"https://www.degruyter.com/document/doi/10.1515/comp-2020-0143/pdf","source":{"id":"https://openalex.org/S4210177004","display_name":"Open Computer Science","issn_l":"2299-1093","issn":["2299-1093"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Open Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.degruyter.com/document/doi/10.1515/comp-2020-0143/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007006229","display_name":"\u0160tefan T\u00f3th","orcid":"https://orcid.org/0000-0003-3047-8534"},"institutions":[{"id":"https://openalex.org/I3122011922","display_name":"University of \u017dilina","ror":"https://ror.org/031wwwj55","country_code":"SK","type":"education","lineage":["https://openalex.org/I3122011922"]}],"countries":["SK"],"is_corresponding":true,"raw_author_name":"\u0160tefan Toth","raw_affiliation_strings":["Department of Software Technologies, Faculty of Management Science and Informatics , University of \u017dilina , \u017dilina , Slovakia"],"affiliations":[{"raw_affiliation_string":"Department of Software Technologies, Faculty of Management Science and Informatics , University of \u017dilina , \u017dilina , Slovakia","institution_ids":["https://openalex.org/I3122011922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069945303","display_name":"Emanuel Zaymus","orcid":null},"institutions":[{"id":"https://openalex.org/I3122011922","display_name":"University of \u017dilina","ror":"https://ror.org/031wwwj55","country_code":"SK","type":"education","lineage":["https://openalex.org/I3122011922"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Emanuel Zaymus","raw_affiliation_strings":["Department of Software Technologies, Faculty of Management Science and Informatics , University of \u017dilina , \u017dilina , Slovakia"],"affiliations":[{"raw_affiliation_string":"Department of Software Technologies, Faculty of Management Science and Informatics , University of \u017dilina , \u017dilina , Slovakia","institution_ids":["https://openalex.org/I3122011922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049343668","display_name":"Michal \u010eura\u010d\u00edk","orcid":"https://orcid.org/0000-0001-9247-039X"},"institutions":[{"id":"https://openalex.org/I3122011922","display_name":"University of \u017dilina","ror":"https://ror.org/031wwwj55","country_code":"SK","type":"education","lineage":["https://openalex.org/I3122011922"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Michal \u010eura\u010d\u00edk","raw_affiliation_strings":["Department of Software Technologies, Faculty of Management Science and Informatics , University of \u017dilina , \u017dilina , Slovakia"],"affiliations":[{"raw_affiliation_string":"Department of Software Technologies, Faculty of Management Science and Informatics , University of \u017dilina , \u017dilina , Slovakia","institution_ids":["https://openalex.org/I3122011922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049203339","display_name":"Patrik Hrk\u00fat","orcid":"https://orcid.org/0000-0002-8747-9194"},"institutions":[{"id":"https://openalex.org/I3122011922","display_name":"University of \u017dilina","ror":"https://ror.org/031wwwj55","country_code":"SK","type":"education","lineage":["https://openalex.org/I3122011922"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Patrik Hrk\u00fat","raw_affiliation_strings":["Department of Software Technologies, Faculty of Management Science and Informatics , University of \u017dilina , \u017dilina , Slovakia"],"affiliations":[{"raw_affiliation_string":"Department of Software Technologies, Faculty of Management Science and Informatics , University of \u017dilina , \u017dilina , Slovakia","institution_ids":["https://openalex.org/I3122011922"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037178535","display_name":"Matej Me\u0161ko","orcid":null},"institutions":[{"id":"https://openalex.org/I3122011922","display_name":"University of \u017dilina","ror":"https://ror.org/031wwwj55","country_code":"SK","type":"education","lineage":["https://openalex.org/I3122011922"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Matej Me\u0161ko","raw_affiliation_strings":["Department of Software Technologies, Faculty of Management Science and Informatics , University of \u017dilina , \u017dilina , Slovakia"],"affiliations":[{"raw_affiliation_string":"Department of Software Technologies, Faculty of Management Science and Informatics , University of \u017dilina , \u017dilina , Slovakia","institution_ids":["https://openalex.org/I3122011922"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5007006229"],"corresponding_institution_ids":["https://openalex.org/I3122011922"],"apc_list":{"value":1000,"currency":"EUR","value_usd":1078},"apc_paid":{"value":1000,"currency":"EUR","value_usd":1078},"fwci":0.4079,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66704317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"11","issue":"1","first_page":"180","last_page":"189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9961000084877014,"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":0.9961000084877014,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.907800018787384,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/slovak","display_name":"Slovak","score":0.834041178226471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6695634126663208},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5863274335861206},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5668818354606628},{"id":"https://openalex.org/keywords/boom","display_name":"Boom","score":0.5599993467330933},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5005605220794678},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48235267400741577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45996955037117004},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.39668357372283936},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11244398355484009},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.110085129737854},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10164234042167664}],"concepts":[{"id":"https://openalex.org/C2780102689","wikidata":"https://www.wikidata.org/wiki/Q9058","display_name":"Slovak","level":3,"score":0.834041178226471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6695634126663208},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5863274335861206},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5668818354606628},{"id":"https://openalex.org/C141441539","wikidata":"https://www.wikidata.org/wiki/Q1970908","display_name":"Boom","level":2,"score":0.5599993467330933},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5005605220794678},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48235267400741577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45996955037117004},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39668357372283936},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11244398355484009},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.110085129737854},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10164234042167664},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1515/comp-2020-0143","is_oa":true,"landing_page_url":"https://doi.org/10.1515/comp-2020-0143","pdf_url":"https://www.degruyter.com/document/doi/10.1515/comp-2020-0143/pdf","source":{"id":"https://openalex.org/S4210177004","display_name":"Open Computer Science","issn_l":"2299-1093","issn":["2299-1093"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Open Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f5db4b66f9fb4cd0bdedbd698c9633b4","is_oa":true,"landing_page_url":"https://doaj.org/article/f5db4b66f9fb4cd0bdedbd698c9633b4","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Open Computer Science, Vol 11, Iss 1, Pp 180-189 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1515/comp-2020-0143","is_oa":true,"landing_page_url":"https://doi.org/10.1515/comp-2020-0143","pdf_url":"https://www.degruyter.com/document/doi/10.1515/comp-2020-0143/pdf","source":{"id":"https://openalex.org/S4210177004","display_name":"Open Computer Science","issn_l":"2299-1093","issn":["2299-1093"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Open Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3131791668.pdf","grobid_xml":"https://content.openalex.org/works/W3131791668.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W16967297","https://openalex.org/W195358446","https://openalex.org/W2153186553","https://openalex.org/W2251939381","https://openalex.org/W2498516793","https://openalex.org/W2573128311","https://openalex.org/W2620499060","https://openalex.org/W2752345823","https://openalex.org/W2790758655","https://openalex.org/W2807585093","https://openalex.org/W2895875496","https://openalex.org/W4241459047"],"related_works":["https://openalex.org/W4213232489","https://openalex.org/W3125406327","https://openalex.org/W2474067781","https://openalex.org/W4383571492","https://openalex.org/W2592002436","https://openalex.org/W4205994876","https://openalex.org/W2765850246","https://openalex.org/W2272734367","https://openalex.org/W2485712061","https://openalex.org/W2468794628"],"abstract_inverted_index":{"Abstract":[0],"Despite":[1],"the":[2,12,33,36,53,118],"modern":[3],"boom":[4],"in":[5,117],"technology,":[6],"we":[7,96],"are":[8,21],"still":[9],"faced":[10],"with":[11,128],"fact":[13],"that":[14,110],"people":[15,43],"write":[16,45],"texts":[17],"without":[18,47,57,63],"diacritics.":[19],"There":[20],"two":[22],"main":[23],"reasons":[24],"for":[25,69,72,132],"this.":[26],"The":[27,49],"first,":[28],"historical":[29],"reason":[30],"stems":[31],"from":[32],"past":[34],"when":[35,88],"use":[37],"of":[38,75,107,114],"diacritics":[39,58,64,78,113],"was":[40],"troublesome":[41],"and":[42,124],"would":[44],"text":[46,115],"them.":[48],"second":[50],"one":[51],"is":[52,59,65,84],"speed":[54],"-":[55],"typing":[56],"usually":[60],"faster.":[61],"Text":[62],"easy":[66],"to":[67],"understand":[68],"people,":[70],"but":[71],"some":[73],"types":[74],"documents,":[76],"missing":[77],"can":[79,111],"cause":[80],"a":[81],"problem.":[82],"This":[83],"also":[85,122],"an":[86,98],"issue":[87],"computers":[89],"process":[90],"such":[91],"text.":[92,134],"In":[93],"this":[94],"paper,":[95],"propose":[97],"algorithm":[99],"based":[100],"on":[101],"word":[102],"n-grams":[103],"(a":[104],"contiguous":[105],"sequence":[106],"n":[108],"words)":[109],"restore":[112],"written":[116],"Slovak":[119,133],"language.":[120],"We":[121],"compare":[123],"evaluate":[125],"our":[126],"results":[127],"other":[129],"algorithms":[130],"developed":[131]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
