{"id":"https://openalex.org/W2117862860","doi":"https://doi.org/10.1186/1687-4722-2014-14","title":"Classification of heterogeneous text data for robust domain-specific language modeling","display_name":"Classification of heterogeneous text data for robust domain-specific language modeling","publication_year":2014,"publication_date":"2014-04-15","ids":{"openalex":"https://openalex.org/W2117862860","doi":"https://doi.org/10.1186/1687-4722-2014-14","mag":"2117862860"},"language":"en","primary_location":{"id":"doi:10.1186/1687-4722-2014-14","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2014-14","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-14","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-14","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075542053","display_name":"J\u00e1n Sta\u0161","orcid":"https://orcid.org/0000-0001-7403-0235"},"institutions":[{"id":"https://openalex.org/I183764125","display_name":"Technical University of Ko\u0161ice","ror":"https://ror.org/05xm08015","country_code":"SK","type":"education","lineage":["https://openalex.org/I183764125"]}],"countries":["SK"],"is_corresponding":true,"raw_author_name":"J\u00e1n Sta\u0161","raw_affiliation_strings":["Department of Electronics and Multimedia Communications, Technical University of Ko\u0161ice, Park Komensk\u00e9ho 13, 041 20, Ko\u0161ice, Slovakia","Department of Electronics and Multimedia Communications, Technical University of Kosice, Ko\u0161ice, Slovakia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Multimedia Communications, Technical University of Ko\u0161ice, Park Komensk\u00e9ho 13, 041 20, Ko\u0161ice, Slovakia","institution_ids":["https://openalex.org/I183764125"]},{"raw_affiliation_string":"Department of Electronics and Multimedia Communications, Technical University of Kosice, Ko\u0161ice, Slovakia","institution_ids":["https://openalex.org/I183764125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060137749","display_name":"Jozef Juh\u00e1r","orcid":"https://orcid.org/0000-0002-1596-9258"},"institutions":[{"id":"https://openalex.org/I183764125","display_name":"Technical University of Ko\u0161ice","ror":"https://ror.org/05xm08015","country_code":"SK","type":"education","lineage":["https://openalex.org/I183764125"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Jozef Juh\u00e1r","raw_affiliation_strings":["Department of Electronics and Multimedia Communications, Technical University of Ko\u0161ice, Park Komensk\u00e9ho 13, 041 20, Ko\u0161ice, Slovakia","Department of Electronics and Multimedia Communications, Technical University of Kosice, Ko\u0161ice, Slovakia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Multimedia Communications, Technical University of Ko\u0161ice, Park Komensk\u00e9ho 13, 041 20, Ko\u0161ice, Slovakia","institution_ids":["https://openalex.org/I183764125"]},{"raw_affiliation_string":"Department of Electronics and Multimedia Communications, Technical University of Kosice, Ko\u0161ice, Slovakia","institution_ids":["https://openalex.org/I183764125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080567273","display_name":"Daniel Hl\u00e1dek","orcid":"https://orcid.org/0000-0003-1148-3194"},"institutions":[{"id":"https://openalex.org/I183764125","display_name":"Technical University of Ko\u0161ice","ror":"https://ror.org/05xm08015","country_code":"SK","type":"education","lineage":["https://openalex.org/I183764125"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Daniel Hl\u00e1dek","raw_affiliation_strings":["Department of Electronics and Multimedia Communications, Technical University of Ko\u0161ice, Park Komensk\u00e9ho 13, 041 20, Ko\u0161ice, Slovakia","Department of Electronics and Multimedia Communications, Technical University of Kosice, Ko\u0161ice, Slovakia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Multimedia Communications, Technical University of Ko\u0161ice, Park Komensk\u00e9ho 13, 041 20, Ko\u0161ice, Slovakia","institution_ids":["https://openalex.org/I183764125"]},{"raw_affiliation_string":"Department of Electronics and Multimedia Communications, Technical University of Kosice, Ko\u0161ice, Slovakia","institution_ids":["https://openalex.org/I183764125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5075542053"],"corresponding_institution_ids":["https://openalex.org/I183764125"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":5.8184,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.95925249,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2014","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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":0.9983999729156494,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9883999824523926,"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/T10028","display_name":"Topic Modeling","score":0.9714000225067139,"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":0.8173526525497437},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7255138158798218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.591249942779541},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.5893235802650452},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5568811297416687},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46748870611190796},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4163323938846588},{"id":"https://openalex.org/keywords/dictation","display_name":"Dictation","score":0.4155995845794678},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4153570830821991},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.2793427109718323}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8173526525497437},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7255138158798218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.591249942779541},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.5893235802650452},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5568811297416687},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46748870611190796},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4163323938846588},{"id":"https://openalex.org/C2779077324","wikidata":"https://www.wikidata.org/wiki/Q1087138","display_name":"Dictation","level":2,"score":0.4155995845794678},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4153570830821991},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2793427109718323},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/1687-4722-2014-14","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2014-14","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-14","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/1687-4722-2014-14","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2014-14","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-14","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6499999761581421,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1518792407","display_name":"Bezpe\u010dnos\u0165 v modern\u00fdch telekomunika\u010dn\u00fdch sie\u0165ach","funder_award_id":"1/0386/12","funder_id":"https://openalex.org/F4320323641","funder_display_name":"Vedeck\u00e1 Grantov\u00e1 Agent\u00fara M\u0160VVa\u0160 SR a SAV"}],"funders":[{"id":"https://openalex.org/F4320321779","display_name":"Ministerstvo \u0161kolstva, vedy, v\u00fdskumu a \u0161portu Slovenskej republiky","ror":"https://ror.org/044gwpv05"},{"id":"https://openalex.org/F4320323641","display_name":"Vedeck\u00e1 Grantov\u00e1 Agent\u00fara M\u0160VVa\u0160 SR a SAV","ror":"https://ror.org/044gwpv05"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2117862860.pdf","grobid_xml":"https://content.openalex.org/works/W2117862860.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W72347498","https://openalex.org/W126222424","https://openalex.org/W195533127","https://openalex.org/W1482214997","https://openalex.org/W1490175560","https://openalex.org/W1532325895","https://openalex.org/W1560796642","https://openalex.org/W1717652683","https://openalex.org/W2033681837","https://openalex.org/W2035259174","https://openalex.org/W2056167975","https://openalex.org/W2076598705","https://openalex.org/W2121082043","https://openalex.org/W2125145463","https://openalex.org/W2140062987","https://openalex.org/W2149684865","https://openalex.org/W2151752770","https://openalex.org/W2165236847","https://openalex.org/W2170079456","https://openalex.org/W2288577906","https://openalex.org/W2397093049","https://openalex.org/W2474958513","https://openalex.org/W2487989883","https://openalex.org/W2494206023","https://openalex.org/W4212980771","https://openalex.org/W4285719527","https://openalex.org/W4307225209"],"related_works":["https://openalex.org/W2093729408","https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4287323699","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2084531783"],"abstract_inverted_index":{"The":[0,20,117,180],"robustness":[1],"of":[2,11,61,75,89,91,127,162,183,205],"n":[3,78],"-gram":[4,79],"language":[5,48,107,187],"models":[6],"depends":[7],"on":[8,14,125,134],"the":[9,58,65,87,99,110,135,141,167,185,191,198,203,206],"quality":[10],"text":[12,21,62,93,121,131,145,164],"data":[13,68,94],"which":[15],"they":[16],"have":[17],"been":[18],"trained.":[19],"corpora":[22],"collected":[23],"from":[24,57,114],"various":[25],"resources":[26],"such":[27],"as":[28,153],"web":[29],"pages":[30],"or":[31],"electronic":[32],"documents":[33],"are":[34,178],"characterized":[35],"by":[36],"many":[37],"possible":[38],"topics.":[39],"In":[40,82,140],"order":[41],"to":[42,53,98,166,190],"build":[43],"efficient":[44],"and":[45,64,101,169,188,201,209],"robust":[46],"domain-specific":[47],"models,":[49],"it":[50],"is":[51,123,147],"necessary":[52],"separate":[54],"domain-oriented":[55],"segments":[56,132,165],"large":[59],"amount":[60],"data,":[63,103],"remaining":[66],"out-of-domain":[67,102],"can":[69],"be":[70],"used":[71,105],"only":[72],"for":[73,106,120],"updating":[74],"existing":[76],"in-domain":[77,100,168],"probability":[80],"estimates.":[81],"this":[83],"paper,":[84],"we":[85],"describe":[86],"process":[88],"classification":[90,122,161],"heterogeneous":[92],"into":[95],"two":[96],"classes,":[97],"mainly":[104],"modeling":[108,184],"in":[109,129,149,197],"task-oriented":[111],"speech":[112],"recognition":[113],"judicial":[115,192],"domain.":[116],"proposed":[118],"algorithm":[119],"based":[124,133],"detection":[126],"theme":[128],"short":[130],"most":[136],"frequent":[137],"key":[138],"phrases.":[139],"next":[142],"step,":[143],"each":[144],"segment":[146],"represented":[148],"vector":[150,156],"space":[151],"model":[152,199],"a":[154],"feature":[155],"with":[157,175],"term":[158],"weighting.":[159],"For":[160],"these":[163],"out-of":[170],"domain":[171,193],"area,":[172],"document":[173],"similarity":[174],"automatic":[176],"thresholding":[177],"used.":[179],"experimental":[181],"results":[182],"Slovak":[186,207],"adaptation":[189],"show":[194],"significant":[195],"improvement":[196],"perplexity":[200],"increasing":[202],"performance":[204],"transcription":[208],"dictation":[210],"system.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
