{"id":"https://openalex.org/W4417095083","doi":"https://doi.org/10.52401/fud/2023/11","title":"PermCorp: egy komi-permj\u00e1k korpusz l\u00e9trehoz\u00e1sa","display_name":"PermCorp: egy komi-permj\u00e1k korpusz l\u00e9trehoz\u00e1sa","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4417095083","doi":"https://doi.org/10.52401/fud/2023/11"},"language":"en","primary_location":{"id":"doi:10.52401/fud/2023/11","doi":"https://doi.org/10.52401/fud/2023/11","is_oa":true,"landing_page_url":"https://doi.org/10.52401/fud/2023/11","pdf_url":"https://doi.org/10.52401/fud/2023/11","source":{"id":"https://openalex.org/S4210229242","display_name":"Folia Uralica Debreceniensia","issn_l":"0239-1953","issn":["0239-1953","2732-3803"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["erih-plus","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Folia Uralica Debreceniensia","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.52401/fud/2023/11","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065725905","display_name":"Szilvia N\u00e9meth","orcid":"https://orcid.org/0009-0004-2625-9659","observed_orcids":["https://orcid.org/0009-0004-2625-9659"]},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]},{"id":"https://openalex.org/I2802350943","display_name":"ELTE Research Centre for Linguistics","ror":"https://ror.org/005cqsz63","country_code":"HU","type":"facility","lineage":["https://openalex.org/I2802350943"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Szilvia N\u00e9meth","raw_affiliation_strings":["E\u00f6tv\u00f6s Lor\u00e1nd Tudom\u00e1nyegyetem , Budapest -","HUN-REN Nyelvtudom\u00e1nyi Kutat\u00f3k\u00f6zpont , Budapest -"],"raw_orcid":"https://orcid.org/0009-0004-2625-9659","affiliations":[{"raw_affiliation_string":"E\u00f6tv\u00f6s Lor\u00e1nd Tudom\u00e1nyegyetem , Budapest -","institution_ids":["https://openalex.org/I106118109"]},{"raw_affiliation_string":"HUN-REN Nyelvtudom\u00e1nyi Kutat\u00f3k\u00f6zpont , Budapest -","institution_ids":["https://openalex.org/I2802350943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113138429","display_name":"Ditta Szab\u00f3","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ditta Szab\u00f3","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5009573694","display_name":"Nikolett F. Guly\u00e1s","orcid":"https://orcid.org/0000-0001-9443-8959","observed_orcids":["https://orcid.org/0000-0001-9443-8959"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolett F. Guly\u00e1s","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9443-8959","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"181","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7383000254631042,"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":0.7383000254631042,"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/T13260","display_name":"Linguistics and Language Studies","score":0.0925000011920929,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13623","display_name":"Linguistic Studies and Language Acquisition","score":0.06480000168085098,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/komi-permyak-language","display_name":"Komi-Permyak language","score":0.9440000057220459},{"id":"https://openalex.org/keywords/glossing","display_name":"glossing","score":0.8859999775886536},{"id":"https://openalex.org/keywords/english-translation","display_name":"English translation","score":0.8619999885559082},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"part-of-speech tagging","score":0.9440000057220459},{"id":"https://openalex.org/keywords/morphological-analysis","display_name":"morphological analysis","score":0.9020000100135803},{"id":"https://openalex.org/keywords/corpus","display_name":"text corpora","score":0.5019999742507935},{"id":"https://openalex.org/keywords/digitalization-of-texts","display_name":"digitalization of texts","score":0.5929999947547913},{"id":"https://openalex.org/keywords/transliteration","display_name":"transliteration","score":0.9520000219345093}],"concepts":[{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.7171000242233276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6977999806404114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6047999858856201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5271999835968018},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5209000110626221},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.4717999994754791},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44110000133514404},{"id":"https://openalex.org/C2987496018","wikidata":"https://www.wikidata.org/wiki/Q1860","display_name":"English language","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C2987219923","wikidata":"https://www.wikidata.org/wiki/Q777864","display_name":"Linguistic analysis","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.26159998774528503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.52401/fud/2023/11","doi":"https://doi.org/10.52401/fud/2023/11","is_oa":true,"landing_page_url":"https://doi.org/10.52401/fud/2023/11","pdf_url":"https://doi.org/10.52401/fud/2023/11","source":{"id":"https://openalex.org/S4210229242","display_name":"Folia Uralica Debreceniensia","issn_l":"0239-1953","issn":["0239-1953","2732-3803"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["erih-plus","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Folia Uralica Debreceniensia","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.52401/fud/2023/11","doi":"https://doi.org/10.52401/fud/2023/11","is_oa":true,"landing_page_url":"https://doi.org/10.52401/fud/2023/11","pdf_url":"https://doi.org/10.52401/fud/2023/11","source":{"id":"https://openalex.org/S4210229242","display_name":"Folia Uralica Debreceniensia","issn_l":"0239-1953","issn":["0239-1953","2732-3803"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["erih-plus","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Folia Uralica Debreceniensia","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417095083.pdf","grobid_xml":"https://content.openalex.org/works/W4417095083.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1648345976","https://openalex.org/W2786574647","https://openalex.org/W3188386801","https://openalex.org/W4393741099","https://openalex.org/W6893786456"],"related_works":["https://openalex.org/W6924884559","https://openalex.org/W4399319314","https://openalex.org/W3087944847","https://openalex.org/W7117971527","https://openalex.org/W4361804597","https://openalex.org/W2995090617","https://openalex.org/W2795230405","https://openalex.org/W2736098086","https://openalex.org/W2042358358","https://openalex.org/W4388965497"],"abstract_inverted_index":{"PermCorp:":[0],"Towards":[1],"the":[2,13,16,24,30,35,49,72,84,88,126,129,133,135,149,153,163,170],"implementation":[3],"of":[4,18,23,29,79,87,103,107,128],"a":[5,20,63,113],"Komi-Permyak":[6,25,52],"corpus":[7,22],"In":[8,94],"this":[9],"paper":[10],"we":[11,99,151],"present":[12],"structure":[14],"and":[15,40,44,116,132,165],"process":[17],"creating":[19],"new":[21],"language.":[26],"The":[27,76],"aim":[28],"project":[31],"is":[32,53,58,81],"to":[33,41,61,70,82,96],"collect":[34],"available":[36],"literature":[37],"in":[38,91,173],"Permyak":[39,89],"provide":[42],"glossing":[43],"English":[45,146,181],"trans-":[46],"lation":[47],"for":[48],"texts.":[50],"Since":[51],"an":[54],"under-researched":[55],"language,":[56],"it":[57],"extremely":[59],"important":[60],"produce":[62],"linguistically":[64],"usable":[65],"text":[66,123],"collection":[67],"that":[68],"contributes":[69],"making":[71],"language":[73,90],"more":[74],"visible.":[75],"primary":[77],"purpose":[78],"PermCorp":[80],"represent":[83],"written":[85],"version":[86],"public":[92],"use.":[93],"order":[95],"do":[97],"this,":[98],"have":[100,118],"collected":[101],"texts":[102,136],"different":[104],"genres,":[105],"each":[106],"which":[108,117],"will":[109,137],"be":[110,138],"represented":[111],"by":[112,122],"sub":[114],"corpus,":[115,176],"been":[119],"ba-":[120],"lanced":[121],"type.":[124],"After":[125],"digitalization":[127],"printed":[130],"works":[131],"transliteration,":[134],"labelled":[139],"with":[140,162],"multi-level":[141],"tagging":[142],"(glossing,":[143],"POS":[144,179],"tagging,":[145,180],"translation).":[147],"During":[148],"project,":[150],"use":[152],"FLEx":[154],"soft-":[155],"ware,":[156],"because":[157],"its":[158],"morphological":[159],"analysis":[160],"function":[161],"dictionary":[164],"grammatical":[166],"outline":[167],"could":[168],"help":[169],"researchers":[171],"effectively":[172],"tagging.":[174],"Keywords:":[175],"Komi-Permyak,":[177],"FLEx,":[178],"translation":[182]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-12-07T00:00:00"}