{"id":"https://openalex.org/W3132002156","doi":"https://doi.org/10.48550/arxiv.2102.12971","title":"Are pre-trained text representations useful for multilingual and multi-dimensional language proficiency modeling?","display_name":"Are pre-trained text representations useful for multilingual and multi-dimensional language proficiency modeling?","publication_year":2021,"publication_date":"2021-02-25","ids":{"openalex":"https://openalex.org/W3132002156","doi":"https://doi.org/10.48550/arxiv.2102.12971","mag":"3132002156"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2102.12971","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.12971","pdf_url":"https://arxiv.org/pdf/2102.12971","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.12971","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030012373","display_name":"Taraka Rama","orcid":"https://orcid.org/0000-0002-4531-6733","observed_orcids":["https://orcid.org/0000-0002-4531-6733"]},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rama, Taraka","raw_affiliation_strings":["University of North Texas , USA","University of North Texas;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Texas , USA","institution_ids":["https://openalex.org/I123534392"]},{"raw_affiliation_string":"University of North Texas;","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030558411","display_name":"Sowmya Vajjala","orcid":"https://orcid.org/0000-0002-4033-9936","observed_orcids":["https://orcid.org/0000-0002-4033-9936"]},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vajjala, Sowmya","raw_affiliation_strings":["National Research Council , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Council , Canada","institution_ids":["https://openalex.org/I4210159778"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5023999810218811,"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/T10028","display_name":"Topic Modeling","score":0.5023999810218811,"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":0.1429000049829483,"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/T11587","display_name":"Second Language Acquisition and Learning","score":0.1152999997138977,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/multilingual-word-embeddings","display_name":"multilingual embeddings","score":0.7829999923706055},{"id":"https://openalex.org/keywords/pre-trained-embeddings","display_name":"pre-trained embeddings","score":0.7229999899864197},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8999999761581421},{"id":"https://openalex.org/keywords/non-native-language-learners","display_name":"non-native language learners","score":0.7549999952316284},{"id":"https://openalex.org/keywords/common-european-framework-of-reference-for-languages","display_name":"Common European Framework of Reference for Languages","score":0.5410000085830688},{"id":"https://openalex.org/keywords/controlled-vocabulary","display_name":"controlled vocabulary","score":0.7229999899864197},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.7170000076293945},{"id":"https://openalex.org/keywords/italian","display_name":"Italian","score":0.9990000128746033},{"id":"https://openalex.org/keywords/czech","display_name":"Czech","score":1.0}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940179109573364},{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.7468727827072144},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.7050075531005859},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6367617249488831},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6004469394683838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5825685262680054},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5542237758636475},{"id":"https://openalex.org/C2778883600","wikidata":"https://www.wikidata.org/wiki/Q2390977","display_name":"Language proficiency","level":2,"score":0.4826946258544922},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.45037615299224854},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3573642671108246},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2102.12971","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.12971","pdf_url":"https://arxiv.org/pdf/2102.12971","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3132002156","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.12971","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2102.12971","doi":"https://doi.org/10.48550/arxiv.2102.12971","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.12971","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.12971","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.12971","pdf_url":"https://arxiv.org/pdf/2102.12971","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.4156000018119812,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"sustainable_development_goals_aurora":[{"score":0.8799999952316284,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1990278592","https://openalex.org/W2101234009","https://openalex.org/W2158240052","https://openalex.org/W2165541489","https://openalex.org/W2250290162","https://openalex.org/W2250372169","https://openalex.org/W2250374950","https://openalex.org/W2250556098","https://openalex.org/W2304127486","https://openalex.org/W2336140400","https://openalex.org/W2564237127","https://openalex.org/W2574640638","https://openalex.org/W2579343286","https://openalex.org/W2775090168","https://openalex.org/W2784454842","https://openalex.org/W2786059534","https://openalex.org/W2796592721","https://openalex.org/W2799207367","https://openalex.org/W2913657017","https://openalex.org/W2948947170","https://openalex.org/W2963341956","https://openalex.org/W2964413085","https://openalex.org/W2970968472","https://openalex.org/W3001808837","https://openalex.org/W3015766957","https://openalex.org/W3016509184","https://openalex.org/W3035009426","https://openalex.org/W3037207300","https://openalex.org/W3037797173","https://openalex.org/W3098654368"],"related_works":["https://openalex.org/W2955383233","https://openalex.org/W2976042047","https://openalex.org/W2983577274","https://openalex.org/W3012990076","https://openalex.org/W2132609289","https://openalex.org/W3211456888","https://openalex.org/W3196383184","https://openalex.org/W2890907172","https://openalex.org/W3136336051","https://openalex.org/W3098041136","https://openalex.org/W2796592721","https://openalex.org/W3175567752","https://openalex.org/W1977305776","https://openalex.org/W3105190698","https://openalex.org/W3097821138","https://openalex.org/W3164871893","https://openalex.org/W1907333498","https://openalex.org/W3181003422","https://openalex.org/W3197148020","https://openalex.org/W3097571385"],"abstract_inverted_index":{"Development":[0],"of":[1,13,62,91,114,124],"language":[2,24,48,72,125],"proficiency":[3,25,73,92,111],"models":[4],"for":[5,18,109,121],"non-native":[6],"learners":[7],"has":[8],"been":[9],"an":[10],"active":[11],"area":[12],"interest":[14],"in":[15,28,68],"NLP":[16],"research":[17,31],"the":[19,60,115],"past":[20],"few":[21],"years.":[22],"Although":[23],"is":[26],"multidimensional":[27],"nature,":[29],"existing":[30,42],"typically":[32],"considers":[33,45],"a":[34,50],"single":[35],"\"overall":[36],"proficiency\"":[37],"while":[38,104],"building":[39],"models.":[40],"Further,":[41],"approaches":[43],"also":[44],"only":[46],"one":[47],"at":[49],"time.":[51],"This":[52],"paper":[53],"describes":[54],"our":[55],"experiments":[56,77],"and":[57,64,84,87,130],"observations":[58],"about":[59],"role":[61],"pre-trained":[63],"fine-tuned":[65,105],"multilingual":[66,71,110],"embeddings":[67,106],"performing":[69],"multi-dimensional,":[70],"classification.":[74],"We":[75],"report":[76],"with":[78],"three":[79],"languages":[80],"--":[81,86],"German,":[82],"Italian,":[83],"Czech":[85],"model":[88],"seven":[89],"dimensions":[90,123],"ranging":[93],"from":[94],"vocabulary":[95],"control":[96],"to":[97],"sociolinguistic":[98],"appropriateness.":[99],"Our":[100],"results":[101],"indicate":[102],"that":[103],"are":[107],"useful":[108],"modeling,":[112],"none":[113],"features":[116],"achieve":[117],"consistently":[118],"best":[119],"performance":[120],"all":[122],"proficiency.":[126],"All":[127],"code,":[128],"data":[129],"related":[131],"supplementary":[132],"material":[133],"can":[134],"be":[135],"found":[136],"at:":[137],"https://github.com/nishkalavallabhi/MultidimCEFRScoring.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2022-07-25T00:00:00"}