{"id":"https://openalex.org/W2095751973","doi":"https://doi.org/10.1142/s0218001409007119","title":"USING DATA-DRIVEN SUBWORD UNITS IN LANGUAGE MODEL OF HIGHLY INFLECTIVE SLOVENIAN LANGUAGE","display_name":"USING DATA-DRIVEN SUBWORD UNITS IN LANGUAGE MODEL OF HIGHLY INFLECTIVE SLOVENIAN LANGUAGE","publication_year":2009,"publication_date":"2009-03-01","ids":{"openalex":"https://openalex.org/W2095751973","doi":"https://doi.org/10.1142/s0218001409007119","mag":"2095751973"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001409007119","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001409007119","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-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/A5055531045","display_name":"Mirjam Sepesy Mau\u010dec","orcid":"https://orcid.org/0000-0003-0215-513X"},"institutions":[{"id":"https://openalex.org/I37696226","display_name":"University of Maribor","ror":"https://ror.org/01d5jce07","country_code":"SI","type":"education","lineage":["https://openalex.org/I37696226"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"MIRJAM SEPESY MAU\u010cEC","raw_affiliation_strings":["Faculty of Electrical Engineering and Computer Science, University of Maribor, Smetanova 17, 2000 Maribor, Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, University of Maribor, Smetanova 17, 2000 Maribor, Slovenia","institution_ids":["https://openalex.org/I37696226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053381792","display_name":"Toma\u017e Rotovnik","orcid":null},"institutions":[{"id":"https://openalex.org/I37696226","display_name":"University of Maribor","ror":"https://ror.org/01d5jce07","country_code":"SI","type":"education","lineage":["https://openalex.org/I37696226"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"TOMA\u017d ROTOVNIK","raw_affiliation_strings":["Faculty of Electrical Engineering and Computer Science, University of Maribor, Smetanova 17, 2000 Maribor, Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, University of Maribor, Smetanova 17, 2000 Maribor, Slovenia","institution_ids":["https://openalex.org/I37696226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072645144","display_name":"Zdravko Ka\u010di\u010d","orcid":"https://orcid.org/0000-0002-8934-0604"},"institutions":[{"id":"https://openalex.org/I37696226","display_name":"University of Maribor","ror":"https://ror.org/01d5jce07","country_code":"SI","type":"education","lineage":["https://openalex.org/I37696226"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"ZDRAVKO KA\u010cI\u010c","raw_affiliation_strings":["Faculty of Electrical Engineering and Computer Science, University of Maribor, Smetanova 17, 2000 Maribor, Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, University of Maribor, Smetanova 17, 2000 Maribor, Slovenia","institution_ids":["https://openalex.org/I37696226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022277993","display_name":"Janez Brest","orcid":"https://orcid.org/0000-0001-5864-3533"},"institutions":[{"id":"https://openalex.org/I37696226","display_name":"University of Maribor","ror":"https://ror.org/01d5jce07","country_code":"SI","type":"education","lineage":["https://openalex.org/I37696226"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"JANEZ BREST","raw_affiliation_strings":["Faculty of Electrical Engineering and Computer Science, University of Maribor, Smetanova 17, 2000 Maribor, Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, University of Maribor, Smetanova 17, 2000 Maribor, Slovenia","institution_ids":["https://openalex.org/I37696226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37696226"],"apc_list":null,"apc_paid":null,"fwci":1.3324,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84593779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"23","issue":"02","first_page":"287","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9919999837875366,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9434999823570251,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.9397649765014648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8415381908416748},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.8263436555862427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.673234224319458},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6364568471908569},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5519482493400574},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.5479642152786255},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4854748547077179},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.47205597162246704},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.46033817529678345},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.45405203104019165},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.44706326723098755},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.42808443307876587},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.31040239334106445},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.17447218298912048},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12356317043304443}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9397649765014648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8415381908416748},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.8263436555862427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.673234224319458},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6364568471908569},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5519482493400574},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.5479642152786255},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4854748547077179},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.47205597162246704},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.46033817529678345},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.45405203104019165},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.44706326723098755},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.42808443307876587},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31040239334106445},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.17447218298912048},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12356317043304443},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001409007119","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001409007119","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1508165687","https://openalex.org/W1988829575","https://openalex.org/W2010910318","https://openalex.org/W2050938027","https://openalex.org/W2069712814","https://openalex.org/W2090750282","https://openalex.org/W2100506586","https://openalex.org/W2101711363","https://openalex.org/W2147169507","https://openalex.org/W2162760965","https://openalex.org/W2190094906"],"related_works":["https://openalex.org/W2151348424","https://openalex.org/W2153295945","https://openalex.org/W2050138804","https://openalex.org/W2787311093","https://openalex.org/W1494910745","https://openalex.org/W2902731467","https://openalex.org/W194986311","https://openalex.org/W1577263324","https://openalex.org/W2082453231","https://openalex.org/W2250551406"],"abstract_inverted_index":{"This":[0,131],"paper":[1],"presents":[2],"the":[3,10,36,54,58,75,90,100,103,124,128,144,148,151,164,179,184,242,248],"results":[4,52],"of":[5,38,57,62,77,89,102,111,127,150],"a":[6,19,23,120,155,170],"study":[7],"on":[8,17,48,193],"modeling":[9],"highly":[11],"inflective":[12],"Slovenian":[13],"language.":[14,59],"We":[15],"focus":[16,46],"creating":[18],"language":[20,42,91,105,152],"model":[21],"for":[22,35,119,154],"large":[24],"vocabulary":[25],"speech":[26,181,190,195,218,254],"recognition":[27,191,219,255],"system.":[28],"A":[29,107],"new":[30],"data-driven":[31],"method":[32],"is":[33,47,66,70,92,113,133],"proposed":[34,202],"induction":[37],"inflectional":[39],"morphology":[40,56],"into":[41,79,99],"modeling.":[43],"The":[44,60,94,159,173,206],"research":[45],"data":[49],"sparsity,":[50],"which":[51,122,212,240],"from":[53,178],"complex":[55],"idea":[61],"using":[63,136,163],"subword":[64,81,95,145],"units":[65,96],"examined.":[67],"An":[68],"attempt":[69],"made":[71],"to":[72],"figure":[73],"out":[74],"segmentation":[76],"words":[78,112],"two":[80],"units:":[82],"stems":[83],"and":[84,203],"endings.":[85],"No":[86],"prior":[87],"knowledge":[88],"used.":[93],"should":[97],"fit":[98],"frameworks":[101],"probabilistic":[104],"models.":[106,138],"morphologically":[108],"correct":[109],"decomposition":[110,121],"not":[114,252],"being":[115],"sought,":[116],"but":[117,239],"searching":[118],"yields":[123],"minimum":[125],"entropy":[126,132],"training":[129,157,171],"corpus.":[130,158,172],"approximated":[134],"by":[135],"N-gram":[137],"Despite":[139],"some":[140],"seemingly":[141],"over-simplified":[142],"assumption,":[143],"models":[146,153,186,200,235],"improve":[147,217,253],"applicability":[149],"sparse":[156],"experiments":[160,192,207],"were":[161,187],"performed":[162],"VE\u010cER":[165],"newswire":[166],"text":[167],"corpus":[168],"as":[169],"test":[174,231],"set":[175,232],"was":[176],"taken":[177],"SNABI":[180,194],"database,":[182],"because":[183],"final":[185],"evaluated":[188],"in":[189],"database.":[196],"Two":[197],"different":[198],"subword-based":[199,210],"are":[201],"examined":[204],"experimentally.":[205],"demonstrate":[208],"that":[209],"models,":[211,226],"considerably":[213],"reduce":[214,241],"OOV":[215,243],"rate,":[216],"WER":[220],"when":[221],"compared":[222],"with":[223,236],"standard":[224],"word-based":[225],"even":[227],"though":[228],"they":[229],"increase":[230],"perplexity.":[233],"Subword-based":[234],"improved":[237],"perplexity,":[238],"rate":[244],"much":[245],"less":[246],"than":[247],"previous":[249],"ones,":[250],"do":[251],"results.":[256]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}