Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324092523> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4324092523 endingPage "3064" @default.
- W4324092523 startingPage "3064" @default.
- W4324092523 abstract "Self-supervised learning models, such as BERT, have improved the performance of various tasks in natural language processing. Although the effect is reduced in the out-of-domain field and not the the trained domain thus representing a limitation, it is difficult to train a new language model for a specific domain since it is both time-consuming and requires large amounts of data. We propose a method to quickly and effectively apply the pre-trained language models trained in the general domain to a specific domain's vocabulary without re-training. An extended vocabulary list is obtained by extracting a meaningful wordpiece from the training data of the downstream task. We introduce curriculum learning, training the models with two successive updates, to adapt the embedding value of the new vocabulary. It is convenient to apply because all training of the models for downstream tasks are performed in one run. To confirm the effectiveness of the proposed method, we conducted experiments on AIDA-SC, AIDA-FC, and KLUE-TC, which are Korean classification tasks, and subsequently achieved stable performance improvement." @default.
- W4324092523 created "2023-03-14" @default.
- W4324092523 creator A5013888370 @default.
- W4324092523 creator A5043236076 @default.
- W4324092523 date "2023-03-13" @default.
- W4324092523 modified "2023-09-26" @default.
- W4324092523 title "Domain Word Extension Using Curriculum Learning" @default.
- W4324092523 cites W1566289585 @default.
- W4324092523 cites W2296073425 @default.
- W4324092523 cites W2801930304 @default.
- W4324092523 cites W2911489562 @default.
- W4324092523 cites W2970771982 @default.
- W4324092523 cites W3035101152 @default.
- W4324092523 cites W3099008231 @default.
- W4324092523 cites W3099950029 @default.
- W4324092523 cites W3199359833 @default.
- W4324092523 cites W3211152275 @default.
- W4324092523 cites W4229443452 @default.
- W4324092523 doi "https://doi.org/10.3390/s23063064" @default.
- W4324092523 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36991775" @default.
- W4324092523 hasPublicationYear "2023" @default.
- W4324092523 type Work @default.
- W4324092523 citedByCount "0" @default.
- W4324092523 crossrefType "journal-article" @default.
- W4324092523 hasAuthorship W4324092523A5013888370 @default.
- W4324092523 hasAuthorship W4324092523A5043236076 @default.
- W4324092523 hasBestOaLocation W43240925231 @default.
- W4324092523 hasConcept C119857082 @default.
- W4324092523 hasConcept C127413603 @default.
- W4324092523 hasConcept C134306372 @default.
- W4324092523 hasConcept C137293760 @default.
- W4324092523 hasConcept C138885662 @default.
- W4324092523 hasConcept C154945302 @default.
- W4324092523 hasConcept C201995342 @default.
- W4324092523 hasConcept C202444582 @default.
- W4324092523 hasConcept C204321447 @default.
- W4324092523 hasConcept C2777462759 @default.
- W4324092523 hasConcept C2777601683 @default.
- W4324092523 hasConcept C2780451532 @default.
- W4324092523 hasConcept C33923547 @default.
- W4324092523 hasConcept C35639132 @default.
- W4324092523 hasConcept C36503486 @default.
- W4324092523 hasConcept C41008148 @default.
- W4324092523 hasConcept C41608201 @default.
- W4324092523 hasConcept C41895202 @default.
- W4324092523 hasConcept C90805587 @default.
- W4324092523 hasConcept C9652623 @default.
- W4324092523 hasConceptScore W4324092523C119857082 @default.
- W4324092523 hasConceptScore W4324092523C127413603 @default.
- W4324092523 hasConceptScore W4324092523C134306372 @default.
- W4324092523 hasConceptScore W4324092523C137293760 @default.
- W4324092523 hasConceptScore W4324092523C138885662 @default.
- W4324092523 hasConceptScore W4324092523C154945302 @default.
- W4324092523 hasConceptScore W4324092523C201995342 @default.
- W4324092523 hasConceptScore W4324092523C202444582 @default.
- W4324092523 hasConceptScore W4324092523C204321447 @default.
- W4324092523 hasConceptScore W4324092523C2777462759 @default.
- W4324092523 hasConceptScore W4324092523C2777601683 @default.
- W4324092523 hasConceptScore W4324092523C2780451532 @default.
- W4324092523 hasConceptScore W4324092523C33923547 @default.
- W4324092523 hasConceptScore W4324092523C35639132 @default.
- W4324092523 hasConceptScore W4324092523C36503486 @default.
- W4324092523 hasConceptScore W4324092523C41008148 @default.
- W4324092523 hasConceptScore W4324092523C41608201 @default.
- W4324092523 hasConceptScore W4324092523C41895202 @default.
- W4324092523 hasConceptScore W4324092523C90805587 @default.
- W4324092523 hasConceptScore W4324092523C9652623 @default.
- W4324092523 hasFunder F4320335489 @default.
- W4324092523 hasIssue "6" @default.
- W4324092523 hasLocation W43240925231 @default.
- W4324092523 hasLocation W43240925232 @default.
- W4324092523 hasLocation W43240925233 @default.
- W4324092523 hasOpenAccess W4324092523 @default.
- W4324092523 hasPrimaryLocation W43240925231 @default.
- W4324092523 hasRelatedWork W1889584887 @default.
- W4324092523 hasRelatedWork W2887872604 @default.
- W4324092523 hasRelatedWork W2944092870 @default.
- W4324092523 hasRelatedWork W2949267551 @default.
- W4324092523 hasRelatedWork W2963033440 @default.
- W4324092523 hasRelatedWork W2988804282 @default.
- W4324092523 hasRelatedWork W3031118452 @default.
- W4324092523 hasRelatedWork W3102086967 @default.
- W4324092523 hasRelatedWork W3184365942 @default.
- W4324092523 hasRelatedWork W4205820553 @default.
- W4324092523 hasVolume "23" @default.
- W4324092523 isParatext "false" @default.
- W4324092523 isRetracted "false" @default.
- W4324092523 workType "article" @default.