{"id":"https://openalex.org/W4312661422","doi":"https://doi.org/10.1007/978-3-031-16500-9_14","title":"Training Dataset and\u00a0Dictionary Sizes Matter in\u00a0BERT Models: The Case of\u00a0Baltic Languages","display_name":"Training Dataset and\u00a0Dictionary Sizes Matter in\u00a0BERT Models: The Case of\u00a0Baltic Languages","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312661422","doi":"https://doi.org/10.1007/978-3-031-16500-9_14"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-16500-9_14","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-16500-9_14","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5056310562","display_name":"Matej Ul\u010dar","orcid":"https://orcid.org/0000-0002-3943-5568"},"institutions":[{"id":"https://openalex.org/I153976015","display_name":"University of Ljubljana","ror":"https://ror.org/05njb9z20","country_code":"SI","type":"education","lineage":["https://openalex.org/I153976015"]}],"countries":["SI"],"is_corresponding":true,"raw_author_name":"Matej Ul\u010dar","raw_affiliation_strings":["Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I153976015"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020021079","display_name":"Marko Robnik\u2010\u0160ikonja","orcid":"https://orcid.org/0000-0002-1232-3320"},"institutions":[{"id":"https://openalex.org/I153976015","display_name":"University of Ljubljana","ror":"https://ror.org/05njb9z20","country_code":"SI","type":"education","lineage":["https://openalex.org/I153976015"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Marko Robnik-\u0160ikonja","raw_affiliation_strings":["Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I153976015"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056310562"],"corresponding_institution_ids":["https://openalex.org/I153976015"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.7123,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87550084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"162","last_page":"172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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/T11719","display_name":"Data Quality and Management","score":0.9616000056266785,"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/latvian","display_name":"Latvian","score":0.9700907468795776},{"id":"https://openalex.org/keywords/estonian","display_name":"Estonian","score":0.9268065690994263},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8884639739990234},{"id":"https://openalex.org/keywords/lithuanian","display_name":"Lithuanian","score":0.8786745071411133},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7013394832611084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6869751214981079},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6573188900947571},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5890758633613586},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5291681289672852},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.48654428124427795},{"id":"https://openalex.org/keywords/dependency-grammar","display_name":"Dependency grammar","score":0.44402486085891724},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4435290992259979},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.27285516262054443}],"concepts":[{"id":"https://openalex.org/C2780375031","wikidata":"https://www.wikidata.org/wiki/Q9078","display_name":"Latvian","level":2,"score":0.9700907468795776},{"id":"https://openalex.org/C2776092919","wikidata":"https://www.wikidata.org/wiki/Q9072","display_name":"Estonian","level":2,"score":0.9268065690994263},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8884639739990234},{"id":"https://openalex.org/C502338164","wikidata":"https://www.wikidata.org/wiki/Q9083","display_name":"Lithuanian","level":2,"score":0.8786745071411133},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7013394832611084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6869751214981079},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6573188900947571},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5890758633613586},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5291681289672852},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.48654428124427795},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.44402486085891724},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4435290992259979},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27285516262054443},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-16500-9_14","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-16500-9_14","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1524281572","https://openalex.org/W2105847779","https://openalex.org/W2398558902","https://openalex.org/W2933138175","https://openalex.org/W2935075866","https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2981852735","https://openalex.org/W3035390927","https://openalex.org/W3082873023","https://openalex.org/W3088130516","https://openalex.org/W3203765809","https://openalex.org/W4391156274","https://openalex.org/W6688866165","https://openalex.org/W6739901393","https://openalex.org/W6778883912","https://openalex.org/W6800751262"],"related_works":["https://openalex.org/W2403613012","https://openalex.org/W2321033754","https://openalex.org/W2505413324","https://openalex.org/W2795733703","https://openalex.org/W4313487331","https://openalex.org/W2315263491","https://openalex.org/W2799450392","https://openalex.org/W2464795768","https://openalex.org/W3032389770","https://openalex.org/W2996519655"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
