Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211955904> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W3211955904 abstract "Recently, domain shift, which affects accuracy due to differences in data between source and target domains, has become a serious issue when using machine learning methods to solve natural language processing tasks. With additional pretraining and fine-tuning using a target domain corpus, pretraining models such as BERT (Bidirectional Encoder Representations from Transformers) can address this issue. However, the additional pretraining of the BERT model is difficult because it requires significant computing resources. The efficiently learning an encoder that classifies token replacements accurately (ELECTRA) pretraining model replaces the BERT pretraining method’s masked language modeling with a method called replaced token detection, which improves the computational efficiency and allows the additional pretraining of the model to a practical extent. Herein, we propose a method for addressing the computational efficiency of pretraining models in domain shift by constructing an ELECTRA pretraining model on a Japanese dataset and additional pretraining this model in a downstream task using a corpus from the target domain. We constructed a pretraining model for ELECTRA in Japanese and conducted experiments on a document classification task using data from Japanese news articles. Results show that even a model smaller than the pretrained model performs equally well." @default.
- W3211955904 created "2021-11-22" @default.
- W3211955904 creator A5008966109 @default.
- W3211955904 creator A5071774468 @default.
- W3211955904 date "2021-01-01" @default.
- W3211955904 modified "2023-09-23" @default.
- W3211955904 title "Domain-Specific Japanese ELECTRA Model Using a Small Corpus" @default.
- W3211955904 cites W2963310665 @default.
- W3211955904 cites W2963341956 @default.
- W3211955904 cites W2971277088 @default.
- W3211955904 doi "https://doi.org/10.26615/978-954-452-072-4_072" @default.
- W3211955904 hasPublicationYear "2021" @default.
- W3211955904 type Work @default.
- W3211955904 sameAs 3211955904 @default.
- W3211955904 citedByCount "0" @default.
- W3211955904 crossrefType "proceedings-article" @default.
- W3211955904 hasAuthorship W3211955904A5008966109 @default.
- W3211955904 hasAuthorship W3211955904A5071774468 @default.
- W3211955904 hasConcept C111919701 @default.
- W3211955904 hasConcept C118505674 @default.
- W3211955904 hasConcept C119857082 @default.
- W3211955904 hasConcept C121332964 @default.
- W3211955904 hasConcept C134306372 @default.
- W3211955904 hasConcept C137293760 @default.
- W3211955904 hasConcept C154945302 @default.
- W3211955904 hasConcept C162324750 @default.
- W3211955904 hasConcept C165801399 @default.
- W3211955904 hasConcept C187736073 @default.
- W3211955904 hasConcept C204321447 @default.
- W3211955904 hasConcept C2780451532 @default.
- W3211955904 hasConcept C28490314 @default.
- W3211955904 hasConcept C33923547 @default.
- W3211955904 hasConcept C36503486 @default.
- W3211955904 hasConcept C38652104 @default.
- W3211955904 hasConcept C41008148 @default.
- W3211955904 hasConcept C48145219 @default.
- W3211955904 hasConcept C62520636 @default.
- W3211955904 hasConcept C66322947 @default.
- W3211955904 hasConceptScore W3211955904C111919701 @default.
- W3211955904 hasConceptScore W3211955904C118505674 @default.
- W3211955904 hasConceptScore W3211955904C119857082 @default.
- W3211955904 hasConceptScore W3211955904C121332964 @default.
- W3211955904 hasConceptScore W3211955904C134306372 @default.
- W3211955904 hasConceptScore W3211955904C137293760 @default.
- W3211955904 hasConceptScore W3211955904C154945302 @default.
- W3211955904 hasConceptScore W3211955904C162324750 @default.
- W3211955904 hasConceptScore W3211955904C165801399 @default.
- W3211955904 hasConceptScore W3211955904C187736073 @default.
- W3211955904 hasConceptScore W3211955904C204321447 @default.
- W3211955904 hasConceptScore W3211955904C2780451532 @default.
- W3211955904 hasConceptScore W3211955904C28490314 @default.
- W3211955904 hasConceptScore W3211955904C33923547 @default.
- W3211955904 hasConceptScore W3211955904C36503486 @default.
- W3211955904 hasConceptScore W3211955904C38652104 @default.
- W3211955904 hasConceptScore W3211955904C41008148 @default.
- W3211955904 hasConceptScore W3211955904C48145219 @default.
- W3211955904 hasConceptScore W3211955904C62520636 @default.
- W3211955904 hasConceptScore W3211955904C66322947 @default.
- W3211955904 hasLocation W32119559041 @default.
- W3211955904 hasOpenAccess W3211955904 @default.
- W3211955904 hasPrimaryLocation W32119559041 @default.
- W3211955904 hasRelatedWork W10803944 @default.
- W3211955904 hasRelatedWork W11223206 @default.
- W3211955904 hasRelatedWork W12023667 @default.
- W3211955904 hasRelatedWork W2085493 @default.
- W3211955904 hasRelatedWork W4052871 @default.
- W3211955904 hasRelatedWork W7737393 @default.
- W3211955904 hasRelatedWork W9233191 @default.
- W3211955904 hasRelatedWork W9266473 @default.
- W3211955904 hasRelatedWork W10597021 @default.
- W3211955904 hasRelatedWork W9519625 @default.
- W3211955904 isParatext "false" @default.
- W3211955904 isRetracted "false" @default.
- W3211955904 magId "3211955904" @default.
- W3211955904 workType "article" @default.