{"id":"https://openalex.org/W4281690961","doi":"https://doi.org/10.3390/make4020025","title":"Benefits from Variational Regularization in Language Models","display_name":"Benefits from Variational Regularization in Language Models","publication_year":2022,"publication_date":"2022-06-09","ids":{"openalex":"https://openalex.org/W4281690961","doi":"https://doi.org/10.3390/make4020025"},"language":"en","primary_location":{"id":"doi:10.3390/make4020025","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make4020025","pdf_url":"https://www.mdpi.com/2504-4990/4/2/25/pdf?version=1654773213","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-4990/4/2/25/pdf?version=1654773213","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000884319","display_name":"Cornelia Ferner","orcid":"https://orcid.org/0000-0003-1721-0453"},"institutions":[{"id":"https://openalex.org/I4210087982","display_name":"Fachhochschule Salzburg","ror":"https://ror.org/0072dxg89","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210087982"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Cornelia Ferner","raw_affiliation_strings":["Information Technology and Systems Management, Salzburg University of Applied Sciences, Urstein Sued 1, 5412 Puch/Hallein, Austria"],"raw_orcid":"https://orcid.org/0000-0003-1721-0453","affiliations":[{"raw_affiliation_string":"Information Technology and Systems Management, Salzburg University of Applied Sciences, Urstein Sued 1, 5412 Puch/Hallein, Austria","institution_ids":["https://openalex.org/I4210087982"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026447617","display_name":"Stefan Wegenkittl","orcid":"https://orcid.org/0000-0002-3297-7997"},"institutions":[{"id":"https://openalex.org/I4210087982","display_name":"Fachhochschule Salzburg","ror":"https://ror.org/0072dxg89","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210087982"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Stefan Wegenkittl","raw_affiliation_strings":["Information Technology and Systems Management, Salzburg University of Applied Sciences, Urstein Sued 1, 5412 Puch/Hallein, Austria"],"raw_orcid":"https://orcid.org/0000-0002-3297-7997","affiliations":[{"raw_affiliation_string":"Information Technology and Systems Management, Salzburg University of Applied Sciences, Urstein Sued 1, 5412 Puch/Hallein, Austria","institution_ids":["https://openalex.org/I4210087982"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000884319"],"corresponding_institution_ids":["https://openalex.org/I4210087982"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.5549,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71446769,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"4","issue":"2","first_page":"542","last_page":"555"},"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9916999936103821,"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/embedding","display_name":"Embedding","score":0.6374291181564331},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6137229800224304},{"id":"https://openalex.org/keywords/isotropy","display_name":"Isotropy","score":0.5874961614608765},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5345228314399719},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48381298780441284},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4833659529685974},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4258868992328644},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4248654246330261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42205560207366943},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41660332679748535},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3680061399936676},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36769992113113403},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13224169611930847}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6374291181564331},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6137229800224304},{"id":"https://openalex.org/C184050105","wikidata":"https://www.wikidata.org/wiki/Q273163","display_name":"Isotropy","level":2,"score":0.5874961614608765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5345228314399719},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48381298780441284},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4833659529685974},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4258868992328644},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4248654246330261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42205560207366943},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41660332679748535},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3680061399936676},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36769992113113403},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13224169611930847},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/make4020025","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make4020025","pdf_url":"https://www.mdpi.com/2504-4990/4/2/25/pdf?version=1654773213","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bf1b4a65b31a452ab3d0e4aa769b3286","is_oa":false,"landing_page_url":"https://doaj.org/article/bf1b4a65b31a452ab3d0e4aa769b3286","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning and Knowledge Extraction, Vol 4, Iss 2, Pp 542-555 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2504-4990/4/2/25/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/make4020025","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/make4020025","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make4020025","pdf_url":"https://www.mdpi.com/2504-4990/4/2/25/pdf?version=1654773213","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281690961.pdf","grobid_xml":"https://content.openalex.org/works/W4281690961.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2594538354","https://openalex.org/W2755124548","https://openalex.org/W2790235966","https://openalex.org/W2892013486","https://openalex.org/W2896457183","https://openalex.org/W2907252220","https://openalex.org/W2948096105","https://openalex.org/W2963216553","https://openalex.org/W2963223306","https://openalex.org/W2963411289","https://openalex.org/W2964212550","https://openalex.org/W2964529779","https://openalex.org/W2964669873","https://openalex.org/W2966574105","https://openalex.org/W2970279348","https://openalex.org/W2970641574","https://openalex.org/W2970682219","https://openalex.org/W2978613765","https://openalex.org/W2988217457","https://openalex.org/W2996657533","https://openalex.org/W2996843693","https://openalex.org/W3024131638","https://openalex.org/W3098708719","https://openalex.org/W3105816068","https://openalex.org/W3116243435","https://openalex.org/W3130089296","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6685356407","https://openalex.org/W6691695795","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W2967478618","https://openalex.org/W2997152889","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W4307309205","https://openalex.org/W4288261899","https://openalex.org/W4387768015","https://openalex.org/W4285141722"],"abstract_inverted_index":{"Representations":[0],"from":[1,11],"common":[2],"pre-trained":[3],"language":[4],"models":[5],"have":[6],"been":[7],"shown":[8],"to":[9,47,68],"suffer":[10],"the":[12,53,57,61,65,110],"degeneration":[13],"problem,":[14],"i.e.,":[15],"they":[16],"occupy":[17],"a":[18,43,48,83],"narrow":[19],"cone":[20],"in":[21,32,60,103],"latent":[22,33,73,104],"space.":[23,34,105],"This":[24,93],"problem":[25],"can":[26,87],"be":[27,88],"addressed":[28],"by":[29],"enforcing":[30],"isotropy":[31],"In":[35],"analogy":[36],"with":[37],"variational":[38,45],"autoencoders,":[39],"we":[40],"suggest":[41],"applying":[42],"token-level":[44],"loss":[46,62],"Transformer":[49],"architecture":[50],"and":[51,77,86],"optimizing":[52],"standard":[54],"deviation":[55],"of":[56],"prior":[58],"distribution":[59],"function":[63],"as":[64,99],"model":[66],"parameter":[67],"increase":[69],"isotropy.":[70],"The":[71],"resulting":[72],"space":[74],"is":[75,82],"complete":[76],"interpretable:":[78],"any":[79],"given":[80],"point":[81],"valid":[84],"embedding":[85],"decoded":[89],"into":[90],"text":[91,96],"again.":[92],"allows":[94],"for":[95],"manipulations":[97],"such":[98],"paraphrase":[100],"generation":[101],"directly":[102],"Surprisingly,":[106],"features":[107],"extracted":[108],"at":[109],"sentence":[111],"level":[112],"also":[113],"show":[114],"competitive":[115],"results":[116],"on":[117],"benchmark":[118],"classification":[119],"tasks.":[120]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}