{"id":"https://openalex.org/W4293199560","doi":"https://doi.org/10.1017/s1351324922000419","title":"RoLEX: The development of an extended Romanian lexical dataset and its evaluation at predicting concurrent lexical information","display_name":"RoLEX: The development of an extended Romanian lexical dataset and its evaluation at predicting concurrent lexical information","publication_year":2022,"publication_date":"2022-08-26","ids":{"openalex":"https://openalex.org/W4293199560","doi":"https://doi.org/10.1017/s1351324922000419"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324922000419","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324922000419","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","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/A5016558880","display_name":"Be\u00e1ta L\u0151rincz","orcid":"https://orcid.org/0000-0002-7728-5863"},"institutions":[{"id":"https://openalex.org/I3125347698","display_name":"Babe\u0219-Bolyai University","ror":"https://ror.org/02rmd1t30","country_code":"RO","type":"education","lineage":["https://openalex.org/I3125347698"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Be\u00e1ta L\u0151rincz","raw_affiliation_strings":["Babe\u015f-Bolyai University, Cluj-Napoca, Romania"],"raw_orcid":"https://orcid.org/0000-0002-7728-5863","affiliations":[{"raw_affiliation_string":"Babe\u015f-Bolyai University, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I3125347698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012740432","display_name":"Elena Irimia","orcid":"https://orcid.org/0000-0002-8910-2809"},"institutions":[{"id":"https://openalex.org/I58077936","display_name":"Romanian Academy","ror":"https://ror.org/0561n6946","country_code":"RO","type":"archive","lineage":["https://openalex.org/I58077936"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Elena Irimia","raw_affiliation_strings":["Research Institute for Artificial Intelligence \u2018Mihai Drag\u0103nescu\u2019, Romanian Academy, Bucharest, Romania","Research Institute for Artificial Intelligence 'Mihai Drag\u0103nescu', Romanian Academy, Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute for Artificial Intelligence \u2018Mihai Drag\u0103nescu\u2019, Romanian Academy, Bucharest, Romania","institution_ids":["https://openalex.org/I58077936"]},{"raw_affiliation_string":"Research Institute for Artificial Intelligence 'Mihai Drag\u0103nescu', Romanian Academy, Bucharest, Romania","institution_ids":["https://openalex.org/I58077936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018126799","display_name":"Adriana Stan","orcid":"https://orcid.org/0000-0003-2894-5770"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adriana Stan","raw_affiliation_strings":["Technical University of Cluj-Napoca, Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006567976","display_name":"Verginica Barbu Mititelu","orcid":"https://orcid.org/0000-0003-1945-2587"},"institutions":[{"id":"https://openalex.org/I58077936","display_name":"Romanian Academy","ror":"https://ror.org/0561n6946","country_code":"RO","type":"archive","lineage":["https://openalex.org/I58077936"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Verginica Barbu Mititelu","raw_affiliation_strings":["Research Institute for Artificial Intelligence \u2018Mihai Drag\u0103nescu\u2019, Romanian Academy, Bucharest, Romania","Research Institute for Artificial Intelligence 'Mihai Drag\u0103nescu', Romanian Academy, Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute for Artificial Intelligence \u2018Mihai Drag\u0103nescu\u2019, Romanian Academy, Bucharest, Romania","institution_ids":["https://openalex.org/I58077936"]},{"raw_affiliation_string":"Research Institute for Artificial Intelligence 'Mihai Drag\u0103nescu', Romanian Academy, Bucharest, Romania","institution_ids":["https://openalex.org/I58077936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016558880"],"corresponding_institution_ids":["https://openalex.org/I3125347698"],"apc_list":null,"apc_paid":null,"fwci":0.4162,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68250236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"29","issue":"3","first_page":"720","last_page":"745"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9987999796867371,"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":0.8770163059234619},{"id":"https://openalex.org/keywords/syllabification","display_name":"Syllabification","score":0.842643141746521},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6445959806442261},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5628002882003784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5490673780441284},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5370380878448486},{"id":"https://openalex.org/keywords/romanian","display_name":"Romanian","score":0.4919266700744629},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4522963762283325},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41997385025024414},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.30553120374679565},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.1668536365032196},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13063672184944153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8770163059234619},{"id":"https://openalex.org/C2779211743","wikidata":"https://www.wikidata.org/wiki/Q11994045","display_name":"Syllabification","level":3,"score":0.842643141746521},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6445959806442261},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5628002882003784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5490673780441284},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5370380878448486},{"id":"https://openalex.org/C129400051","wikidata":"https://www.wikidata.org/wiki/Q7913","display_name":"Romanian","level":2,"score":0.4919266700744629},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4522963762283325},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41997385025024414},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30553120374679565},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.1668536365032196},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13063672184944153},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324922000419","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324922000419","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W10910819","https://openalex.org/W69867230","https://openalex.org/W118182991","https://openalex.org/W122244083","https://openalex.org/W178106347","https://openalex.org/W1529912373","https://openalex.org/W1593247906","https://openalex.org/W1647671624","https://openalex.org/W1978044866","https://openalex.org/W2042547117","https://openalex.org/W2133932086","https://openalex.org/W2136978972","https://openalex.org/W2152748510","https://openalex.org/W2163925746","https://openalex.org/W2251114096","https://openalex.org/W2251295238","https://openalex.org/W2510721042","https://openalex.org/W2538246917","https://openalex.org/W2591557889","https://openalex.org/W2612690371","https://openalex.org/W2735039859","https://openalex.org/W2738884019","https://openalex.org/W2741147977","https://openalex.org/W2748157908","https://openalex.org/W2757558076","https://openalex.org/W2785629297","https://openalex.org/W2805269870","https://openalex.org/W2805957826","https://openalex.org/W2884873108","https://openalex.org/W2896457183","https://openalex.org/W2920834369","https://openalex.org/W2924505532","https://openalex.org/W2963299674","https://openalex.org/W2972437137","https://openalex.org/W2972677740","https://openalex.org/W2989746191","https://openalex.org/W3029923669","https://openalex.org/W3090288252","https://openalex.org/W3095623868","https://openalex.org/W3096083295","https://openalex.org/W3097731840","https://openalex.org/W3208065268","https://openalex.org/W4232808712","https://openalex.org/W6636915900","https://openalex.org/W6737778391","https://openalex.org/W6775227608","https://openalex.org/W6797674293"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W1585014485","https://openalex.org/W2081647779","https://openalex.org/W2019914509","https://openalex.org/W3185852197","https://openalex.org/W3209879215","https://openalex.org/W1937192591","https://openalex.org/W3101868899","https://openalex.org/W1539050421","https://openalex.org/W2140165763"],"abstract_inverted_index":{"Abstract":[0],"In":[1,219],"this":[2,32,184],"article,":[3],"we":[4],"introduce":[5],"an":[6],"extended,":[7],"freely":[8],"available":[9],"resource":[10],"for":[11,23,114,196,233],"the":[12,56,64,72,108,117,120,130,133,141,147,156,160,165,205,224,237,240],"Romanian":[13],"language,":[14],"named":[15],"RoLEX":[16,34],".":[17],"The":[18,52,77,98,150],"dataset":[19,103],"was":[20,162],"developed":[21],"mainly":[22],"speech":[24],"processing":[25],"applications,":[26],"yet":[27],"its":[28],"applicability":[29],"extends":[30],"beyond":[31],"domain.":[33],"includes":[35],"over":[36],"330,000":[37],"curated":[38],"entries":[39,60,73,113,125,161,195,215],"with":[40,69,135,164],"information":[41,67],"regarding":[42],"lemma,":[43],"morphosyntactic":[44,136,167],"description,":[45],"syllabification,":[46,91],"lexical":[47,66,92,225],"stress":[48,93,226],"and":[49,61,95,129,175,231],"phonemic":[50,96],"transcription.":[51,97],"process":[53],"of":[54,58,71,87,90,112,119,123,132,143,159,173,180,194,212,221,236],"selecting":[55],"list":[57],"word":[59,170],"semi-automatically":[62],"annotating":[63],"complete":[65,166],"associated":[68],"each":[70,144],"is":[74,81],"thoroughly":[75],"described.":[76],"dataset\u2019s":[78],"inherent":[79],"knowledge":[80],"then":[82],"evaluated":[83],"in":[84,146,200,239],"a":[85,176,190,201,209],"task":[86,145],"concurrent":[88],"prediction":[89,222],"marking":[94,227],"evaluation":[99],"looked":[100],"into":[101],"several":[102],"design":[104],"factors,":[105],"such":[106],"as":[107,138,140,217],"minimum":[109,121],"viable":[110],"number":[111,122],"correct":[115],"prediction,":[116],"optimisation":[118],"required":[124],"through":[126],"expert":[127],"selection":[128],"augmentation":[131],"input":[134],"information,":[137],"well":[139],"influence":[142],"overall":[148],"accuracy.":[149],"best":[151],"results":[152],"were":[153,182],"obtained":[154,183,207],"when":[155],"orthographic":[157],"form":[158],"augmented":[163],"tags.":[168],"A":[169],"error":[171,178],"rate":[172,179],"3.08%":[174],"character":[177],"1.08%":[181],"way.":[185],"We":[186],"show":[187],"that":[188],"using":[189],"carefully":[191],"selected":[192,214],"subset":[193],"training":[197],"can":[198],"result":[199],"similar":[202],"performance":[203,206],"to":[204],"by":[208],"larger":[210],"set":[211],"randomly":[213],"(twice":[216],"many).":[218],"terms":[220],"complexity,":[223],"posed":[228],"most":[229],"problems":[230],"accounts":[232],"around":[234],"60%":[235],"errors":[238],"predicted":[241],"sequence.":[242]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}