{"id":"https://openalex.org/W3089204009","doi":"https://doi.org/10.3233/faia200597","title":"Evaluating Multilingual BERT for Estonian","display_name":"Evaluating Multilingual BERT for Estonian","publication_year":2020,"publication_date":"2020-09-15","ids":{"openalex":"https://openalex.org/W3089204009","doi":"https://doi.org/10.3233/faia200597","mag":"3089204009"},"language":"en","primary_location":{"id":"doi:10.3233/faia200597","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200597","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200597","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200597","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005102164","display_name":"Claudia Kittask","orcid":null},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":true,"raw_author_name":"Claudia Kittask","raw_affiliation_strings":["Institute of Computer Science, University of Tartu, Estonia"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of Tartu, Estonia","institution_ids":["https://openalex.org/I56085075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081917232","display_name":"Kirill Milintsevich","orcid":"https://orcid.org/0000-0001-9253-1682"},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Kirill Milintsevich","raw_affiliation_strings":["Institute of Computer Science, University of Tartu, Estonia"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of Tartu, Estonia","institution_ids":["https://openalex.org/I56085075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035358986","display_name":"Kairit Sirts","orcid":"https://orcid.org/0000-0001-7388-2583"},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Kairit Sirts","raw_affiliation_strings":["Institute of Computer Science, University of Tartu, Estonia"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of Tartu, Estonia","institution_ids":["https://openalex.org/I56085075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005102164"],"corresponding_institution_ids":["https://openalex.org/I56085075"],"apc_list":null,"apc_paid":null,"fwci":0.52145642,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67689491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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/T11719","display_name":"Data Quality and Management","score":0.9789000153541565,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/estonian","display_name":"Estonian","score":0.9590010046958923},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8403120040893555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6859921813011169},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.679387092590332},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6115072965621948},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5785565376281738},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4472103714942932},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16821974515914917},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.13423147797584534}],"concepts":[{"id":"https://openalex.org/C2776092919","wikidata":"https://www.wikidata.org/wiki/Q9072","display_name":"Estonian","level":2,"score":0.9590010046958923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8403120040893555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6859921813011169},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.679387092590332},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6115072965621948},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5785565376281738},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4472103714942932},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16821974515914917},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.13423147797584534},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3233/faia200597","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200597","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200597","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2010.00454","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.00454","pdf_url":"https://arxiv.org/pdf/2010.00454","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:3089204009","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.00454.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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.2010.00454","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.00454","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"}],"best_oa_location":{"id":"doi:10.3233/faia200597","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200597","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200597","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8899999856948853}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3089204009.pdf","grobid_xml":"https://content.openalex.org/works/W3089204009.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W70071972","https://openalex.org/W2250923910","https://openalex.org/W2741029840","https://openalex.org/W2880875857","https://openalex.org/W2946676565","https://openalex.org/W2952638691","https://openalex.org/W2962739339","https://openalex.org/W2963341956","https://openalex.org/W2963626623","https://openalex.org/W2965373594","https://openalex.org/W2970049541","https://openalex.org/W2970529259","https://openalex.org/W2978017171","https://openalex.org/W2982364408","https://openalex.org/W2983040767","https://openalex.org/W2995647371","https://openalex.org/W3009095382","https://openalex.org/W3011573503","https://openalex.org/W3037109418","https://openalex.org/W6748634344"],"related_works":["https://openalex.org/W3165478185","https://openalex.org/W3174015120","https://openalex.org/W3082873023","https://openalex.org/W3035262097","https://openalex.org/W2995647371","https://openalex.org/W2973071945","https://openalex.org/W3185236989","https://openalex.org/W3080175947","https://openalex.org/W3136336051","https://openalex.org/W3094458375","https://openalex.org/W3088262928","https://openalex.org/W2982364408","https://openalex.org/W3096266342","https://openalex.org/W3008086364","https://openalex.org/W3158835769","https://openalex.org/W2976042047","https://openalex.org/W3197261271","https://openalex.org/W3211456888","https://openalex.org/W2983577274","https://openalex.org/W3212869160"],"abstract_inverted_index":{"Recently,":[0],"large":[1],"pre-trained":[2],"language":[3,15],"models,":[4],"such":[5],"as":[6],"BERT,":[7,60,63],"have":[8,45],"reached":[9],"state-of-the-art":[10],"performance":[11],"in":[12],"many":[13,20],"natural":[14],"processing":[16],"tasks,":[17],"but":[18],"for":[19,97,119,136],"languages,":[21],"including":[22,70],"Estonian,":[23],"BERT":[24,35,89,105],"models":[25,36,90,96,106,118],"are":[26],"not":[27],"yet":[28],"available.":[29],"However,":[30],"there":[31],"exist":[32],"several":[33,67],"multilingual":[34,58,61,88,104,147],"that":[37,44,103],"can":[38,107],"handle":[39],"multiple":[40],"languages":[41],"simultaneously":[42],"and":[43,65,72,76,91,121,124,127],"been":[46],"trained":[47],"also":[48],"on":[49,110],"Estonian":[50,112],"data.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"evaluate":[56],"four":[57],"models\u2014multilingual":[59],"distilled":[62],"XLM":[64],"XLM-RoBERTa\u2014on":[66],"NLP":[68,113],"tasks":[69,114],"POS":[71,120],"morphological":[73,122],"tagging,":[74],"NER":[75],"text":[77,125],"classification.":[78],"Our":[79,100],"aim":[80],"is":[81],"to":[82],"establish":[83],"a":[84],"comparison":[85],"between":[86],"these":[87,98],"the":[92,129,133,141],"existing":[93],"baseline":[94,135],"neural":[95],"tasks.":[99],"results":[101,143],"show":[102],"generalise":[108],"well":[109],"different":[111],"outperforming":[115],"all":[116],"baselines":[117],"tagging":[123],"classification,":[126],"reaching":[128],"comparable":[130],"level":[131],"with":[132,138,145],"best":[134],"NER,":[137],"XLM-RoBERTa":[139],"achieving":[140],"highest":[142],"compared":[144],"other":[146],"models.":[148]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}
