Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313215605> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4313215605 endingPage "103194" @default.
- W4313215605 startingPage "103194" @default.
- W4313215605 abstract "The application of natural language processing (NLP) to financial fields is advancing with an increase in the number of available financial documents. Transformer-based models such as Bidirectional Encoder Representations from Transformers (BERT) have been successful in NLP in recent years. These cutting-edge models have been adapted to the financial domain by applying financial corpora to existing pre-trained models and by pre-training with the financial corpora from scratch. In Japanese, by contrast, financial terminology cannot be applied from a general vocabulary without further processing. In this study, we construct language models suitable for the financial domain. Furthermore, we compare methods for adapting language models to the financial domain, such as pre-training methods and vocabulary adaptation. We confirm that the adaptation of a pre-training corpus and tokenizer vocabulary based on a corpus of financial text is effective in several downstream financial tasks. No significant difference is observed between pre-training with the financial corpus and continuous pre-training from the general language model with the financial corpus. We have released our source code and pre-trained models." @default.
- W4313215605 created "2023-01-06" @default.
- W4313215605 creator A5002301422 @default.
- W4313215605 creator A5028823648 @default.
- W4313215605 creator A5038802330 @default.
- W4313215605 creator A5044205949 @default.
- W4313215605 date "2023-03-01" @default.
- W4313215605 modified "2023-09-30" @default.
- W4313215605 title "Constructing and analyzing domain-specific language model for financial text mining" @default.
- W4313215605 cites W1546425147 @default.
- W4313215605 cites W1947985544 @default.
- W4313215605 cites W2015174807 @default.
- W4313215605 cites W2064675550 @default.
- W4313215605 cites W2065686820 @default.
- W4313215605 cites W2096935314 @default.
- W4313215605 cites W2131774270 @default.
- W4313215605 cites W2171468534 @default.
- W4313215605 cites W2493916176 @default.
- W4313215605 cites W2529087958 @default.
- W4313215605 cites W2911489562 @default.
- W4313215605 cites W3160137267 @default.
- W4313215605 cites W4220918998 @default.
- W4313215605 doi "https://doi.org/10.1016/j.ipm.2022.103194" @default.
- W4313215605 hasPublicationYear "2023" @default.
- W4313215605 type Work @default.
- W4313215605 citedByCount "2" @default.
- W4313215605 countsByYear W43132156052023 @default.
- W4313215605 crossrefType "journal-article" @default.
- W4313215605 hasAuthorship W4313215605A5002301422 @default.
- W4313215605 hasAuthorship W4313215605A5028823648 @default.
- W4313215605 hasAuthorship W4313215605A5038802330 @default.
- W4313215605 hasAuthorship W4313215605A5044205949 @default.
- W4313215605 hasConcept C10138342 @default.
- W4313215605 hasConcept C111919701 @default.
- W4313215605 hasConcept C118505674 @default.
- W4313215605 hasConcept C121332964 @default.
- W4313215605 hasConcept C137293760 @default.
- W4313215605 hasConcept C138885662 @default.
- W4313215605 hasConcept C154945302 @default.
- W4313215605 hasConcept C162324750 @default.
- W4313215605 hasConcept C165801399 @default.
- W4313215605 hasConcept C204321447 @default.
- W4313215605 hasConcept C2474386 @default.
- W4313215605 hasConcept C2776434776 @default.
- W4313215605 hasConcept C2777601683 @default.
- W4313215605 hasConcept C41008148 @default.
- W4313215605 hasConcept C41895202 @default.
- W4313215605 hasConcept C547195049 @default.
- W4313215605 hasConcept C62520636 @default.
- W4313215605 hasConcept C66322947 @default.
- W4313215605 hasConcept C95623464 @default.
- W4313215605 hasConceptScore W4313215605C10138342 @default.
- W4313215605 hasConceptScore W4313215605C111919701 @default.
- W4313215605 hasConceptScore W4313215605C118505674 @default.
- W4313215605 hasConceptScore W4313215605C121332964 @default.
- W4313215605 hasConceptScore W4313215605C137293760 @default.
- W4313215605 hasConceptScore W4313215605C138885662 @default.
- W4313215605 hasConceptScore W4313215605C154945302 @default.
- W4313215605 hasConceptScore W4313215605C162324750 @default.
- W4313215605 hasConceptScore W4313215605C165801399 @default.
- W4313215605 hasConceptScore W4313215605C204321447 @default.
- W4313215605 hasConceptScore W4313215605C2474386 @default.
- W4313215605 hasConceptScore W4313215605C2776434776 @default.
- W4313215605 hasConceptScore W4313215605C2777601683 @default.
- W4313215605 hasConceptScore W4313215605C41008148 @default.
- W4313215605 hasConceptScore W4313215605C41895202 @default.
- W4313215605 hasConceptScore W4313215605C547195049 @default.
- W4313215605 hasConceptScore W4313215605C62520636 @default.
- W4313215605 hasConceptScore W4313215605C66322947 @default.
- W4313215605 hasConceptScore W4313215605C95623464 @default.
- W4313215605 hasFunder F4320334764 @default.
- W4313215605 hasFunder F4320338243 @default.
- W4313215605 hasIssue "2" @default.
- W4313215605 hasLocation W43132156051 @default.
- W4313215605 hasOpenAccess W4313215605 @default.
- W4313215605 hasPrimaryLocation W43132156051 @default.
- W4313215605 hasRelatedWork W2547835662 @default.
- W4313215605 hasRelatedWork W2945824677 @default.
- W4313215605 hasRelatedWork W3033942572 @default.
- W4313215605 hasRelatedWork W3097571385 @default.
- W4313215605 hasRelatedWork W3098382480 @default.
- W4313215605 hasRelatedWork W3104417388 @default.
- W4313215605 hasRelatedWork W3161911362 @default.
- W4313215605 hasRelatedWork W3196747313 @default.
- W4313215605 hasRelatedWork W4237966389 @default.
- W4313215605 hasRelatedWork W4287598411 @default.
- W4313215605 hasVolume "60" @default.
- W4313215605 isParatext "false" @default.
- W4313215605 isRetracted "false" @default.
- W4313215605 workType "article" @default.