Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200380247> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4200380247 endingPage "718" @default.
- W4200380247 startingPage "709" @default.
- W4200380247 abstract "Trained on a large corpus, pretrained models (PTMs) can capture different levels of concepts in context and hence generate universal language representations, which greatly benefit downstream natural language processing (NLP) tasks. In recent years, PTMs have been widely used in most NLP applications, especially for high-resource languages, such as English and Chinese. However, scarce resources have discouraged the progress of PTMs for low-resource languages. Transformer-based PTMs for the Khmer language are presented in this work for the first time. We evaluate our models on two downstream tasks: Part-of-speech tagging and news categorization. The dataset for the latter task is self-constructed. Experiments demonstrate the effectiveness of the Khmer models. In addition, we find that the current Khmer word segmentation technology does not aid performance improvement. We aim to release our models and datasets to the community in hopes of facilitating the future development of Khmer NLP applications." @default.
- W4200380247 created "2021-12-31" @default.
- W4200380247 creator A5014108621 @default.
- W4200380247 creator A5018477994 @default.
- W4200380247 creator A5070480766 @default.
- W4200380247 creator A5084625962 @default.
- W4200380247 date "2022-08-01" @default.
- W4200380247 modified "2023-09-26" @default.
- W4200380247 title "Pretrained models and evaluation data for the Khmer language" @default.
- W4200380247 doi "https://doi.org/10.26599/tst.2021.9010060" @default.
- W4200380247 hasPublicationYear "2022" @default.
- W4200380247 type Work @default.
- W4200380247 citedByCount "6" @default.
- W4200380247 countsByYear W42003802472022 @default.
- W4200380247 countsByYear W42003802472023 @default.
- W4200380247 crossrefType "journal-article" @default.
- W4200380247 hasAuthorship W4200380247A5014108621 @default.
- W4200380247 hasAuthorship W4200380247A5018477994 @default.
- W4200380247 hasAuthorship W4200380247A5070480766 @default.
- W4200380247 hasAuthorship W4200380247A5084625962 @default.
- W4200380247 hasBestOaLocation W42003802471 @default.
- W4200380247 hasConcept C119599485 @default.
- W4200380247 hasConcept C127413603 @default.
- W4200380247 hasConcept C137293760 @default.
- W4200380247 hasConcept C151730666 @default.
- W4200380247 hasConcept C154945302 @default.
- W4200380247 hasConcept C165801399 @default.
- W4200380247 hasConcept C201995342 @default.
- W4200380247 hasConcept C204321447 @default.
- W4200380247 hasConcept C206345919 @default.
- W4200380247 hasConcept C2779343474 @default.
- W4200380247 hasConcept C2780451532 @default.
- W4200380247 hasConcept C31258907 @default.
- W4200380247 hasConcept C41008148 @default.
- W4200380247 hasConcept C66322947 @default.
- W4200380247 hasConcept C86803240 @default.
- W4200380247 hasConcept C94124525 @default.
- W4200380247 hasConceptScore W4200380247C119599485 @default.
- W4200380247 hasConceptScore W4200380247C127413603 @default.
- W4200380247 hasConceptScore W4200380247C137293760 @default.
- W4200380247 hasConceptScore W4200380247C151730666 @default.
- W4200380247 hasConceptScore W4200380247C154945302 @default.
- W4200380247 hasConceptScore W4200380247C165801399 @default.
- W4200380247 hasConceptScore W4200380247C201995342 @default.
- W4200380247 hasConceptScore W4200380247C204321447 @default.
- W4200380247 hasConceptScore W4200380247C206345919 @default.
- W4200380247 hasConceptScore W4200380247C2779343474 @default.
- W4200380247 hasConceptScore W4200380247C2780451532 @default.
- W4200380247 hasConceptScore W4200380247C31258907 @default.
- W4200380247 hasConceptScore W4200380247C41008148 @default.
- W4200380247 hasConceptScore W4200380247C66322947 @default.
- W4200380247 hasConceptScore W4200380247C86803240 @default.
- W4200380247 hasConceptScore W4200380247C94124525 @default.
- W4200380247 hasIssue "4" @default.
- W4200380247 hasLocation W42003802471 @default.
- W4200380247 hasOpenAccess W4200380247 @default.
- W4200380247 hasPrimaryLocation W42003802471 @default.
- W4200380247 hasRelatedWork W2359001871 @default.
- W4200380247 hasRelatedWork W3008110149 @default.
- W4200380247 hasRelatedWork W3033862527 @default.
- W4200380247 hasRelatedWork W3033942572 @default.
- W4200380247 hasRelatedWork W3097571385 @default.
- W4200380247 hasRelatedWork W3196747313 @default.
- W4200380247 hasRelatedWork W4205820553 @default.
- W4200380247 hasRelatedWork W4287761227 @default.
- W4200380247 hasRelatedWork W4291908500 @default.
- W4200380247 hasRelatedWork W4381786178 @default.
- W4200380247 hasVolume "27" @default.
- W4200380247 isParatext "false" @default.
- W4200380247 isRetracted "false" @default.
- W4200380247 workType "article" @default.