FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048707928> ?p ?o ?g. }

• W3048707928 abstract "End-to-end Spoken Language Understanding (SLU) models are made increasingly large and complex to achieve the state-ofthe-art accuracy. However, the increased complexity of a model can also introduce high risk of over-fitting, which is a major challenge in SLU tasks due to the limitation of available data. In this paper, we propose an attention-based SLU model together with three encoder enhancement strategies to overcome data sparsity challenge. The first strategy focuses on the transferlearning approach to improve feature extraction capability of the encoder. It is implemented by pre-training the encoder component with a quantity of Automatic Speech Recognition annotated data relying on the standard Transformer architecture and then fine-tuning the SLU model with a small amount of target labelled data. The second strategy adopts multitask learning strategy, the SLU model integrates the speech recognition model by sharing the same underlying encoder, such that improving robustness and generalization ability. The third strategy, learning from Component Fusion (CF) idea, involves a Bidirectional Encoder Representation from Transformer (BERT) model and aims to boost the capability of the decoder with an auxiliary network. It hence reduces the risk of over-fitting and augments the ability of the underlying encoder, indirectly. Experiments on the FluentAI dataset show that cross-language transfer learning and multi-task strategies have been improved by up to 4:52% and 3:89% respectively, compared to the baseline." @default.
• W3048707928 created "2020-08-18" @default.
• W3048707928 creator A5016038454 @default.
• W3048707928 creator A5021905687 @default.
• W3048707928 creator A5044129044 @default.
• W3048707928 creator A5074472751 @default.
• W3048707928 creator A5084554132 @default.
• W3048707928 date "2020-10-25" @default.
• W3048707928 modified "2023-09-23" @default.
• W3048707928 title "Large-Scale Transfer Learning for Low-Resource Spoken Language Understanding" @default.
• W3048707928 cites W1549576988 @default.
• W3048707928 cites W196214544 @default.
• W3048707928 cites W2130942839 @default.
• W3048707928 cites W2499126254 @default.
• W3048707928 cites W2752788177 @default.
• W3048707928 cites W2887280559 @default.
• W3048707928 cites W2888940013 @default.
• W3048707928 cites W2891229414 @default.
• W3048707928 cites W2894164357 @default.
• W3048707928 cites W2936078256 @default.
• W3048707928 cites W2936123380 @default.
• W3048707928 cites W2939111082 @default.
• W3048707928 cites W2963027641 @default.
• W3048707928 cites W2963229292 @default.
• W3048707928 cites W2963288440 @default.
• W3048707928 cites W2963341956 @default.
• W3048707928 cites W2963403868 @default.
• W3048707928 cites W2963578416 @default.
• W3048707928 cites W2964108264 @default.
• W3048707928 cites W2964161387 @default.
• W3048707928 cites W2964313990 @default.
• W3048707928 cites W2972314145 @default.
• W3048707928 cites W2972327934 @default.
• W3048707928 cites W2972525948 @default.
• W3048707928 cites W2972584841 @default.
• W3048707928 cites W2972698273 @default.
• W3048707928 cites W2973175287 @default.
• W3048707928 cites W2998814410 @default.
• W3048707928 cites W3015412890 @default.
• W3048707928 cites W3015654466 @default.
• W3048707928 cites W3015752032 @default.
• W3048707928 cites W3015974384 @default.
• W3048707928 cites W3016006013 @default.
• W3048707928 doi "https://doi.org/10.21437/interspeech.2020-59" @default.
• W3048707928 hasPublicationYear "2020" @default.
• W3048707928 type Work @default.
• W3048707928 sameAs 3048707928 @default.
• W3048707928 citedByCount "3" @default.
• W3048707928 countsByYear W30487079282020 @default.
• W3048707928 countsByYear W30487079282021 @default.
• W3048707928 crossrefType "proceedings-article" @default.
• W3048707928 hasAuthorship W3048707928A5016038454 @default.
• W3048707928 hasAuthorship W3048707928A5021905687 @default.
• W3048707928 hasAuthorship W3048707928A5044129044 @default.
• W3048707928 hasAuthorship W3048707928A5074472751 @default.
• W3048707928 hasAuthorship W3048707928A5084554132 @default.
• W3048707928 hasBestOaLocation W30487079282 @default.
• W3048707928 hasConcept C104317684 @default.
• W3048707928 hasConcept C108583219 @default.
• W3048707928 hasConcept C111919701 @default.
• W3048707928 hasConcept C118505674 @default.
• W3048707928 hasConcept C119857082 @default.
• W3048707928 hasConcept C121332964 @default.
• W3048707928 hasConcept C137293760 @default.
• W3048707928 hasConcept C150899416 @default.
• W3048707928 hasConcept C154945302 @default.
• W3048707928 hasConcept C162324750 @default.
• W3048707928 hasConcept C165801399 @default.
• W3048707928 hasConcept C185592680 @default.
• W3048707928 hasConcept C187736073 @default.
• W3048707928 hasConcept C2780451532 @default.
• W3048707928 hasConcept C28006648 @default.
• W3048707928 hasConcept C28490314 @default.
• W3048707928 hasConcept C41008148 @default.
• W3048707928 hasConcept C55493867 @default.
• W3048707928 hasConcept C59404180 @default.
• W3048707928 hasConcept C62520636 @default.
• W3048707928 hasConcept C63479239 @default.
• W3048707928 hasConcept C66322947 @default.
• W3048707928 hasConcept C74296488 @default.
• W3048707928 hasConceptScore W3048707928C104317684 @default.
• W3048707928 hasConceptScore W3048707928C108583219 @default.
• W3048707928 hasConceptScore W3048707928C111919701 @default.
• W3048707928 hasConceptScore W3048707928C118505674 @default.
• W3048707928 hasConceptScore W3048707928C119857082 @default.
• W3048707928 hasConceptScore W3048707928C121332964 @default.
• W3048707928 hasConceptScore W3048707928C137293760 @default.
• W3048707928 hasConceptScore W3048707928C150899416 @default.
• W3048707928 hasConceptScore W3048707928C154945302 @default.
• W3048707928 hasConceptScore W3048707928C162324750 @default.
• W3048707928 hasConceptScore W3048707928C165801399 @default.
• W3048707928 hasConceptScore W3048707928C185592680 @default.
• W3048707928 hasConceptScore W3048707928C187736073 @default.
• W3048707928 hasConceptScore W3048707928C2780451532 @default.
• W3048707928 hasConceptScore W3048707928C28006648 @default.
• W3048707928 hasConceptScore W3048707928C28490314 @default.
• W3048707928 hasConceptScore W3048707928C41008148 @default.
• W3048707928 hasConceptScore W3048707928C55493867 @default.
• W3048707928 hasConceptScore W3048707928C59404180 @default.
• W3048707928 hasConceptScore W3048707928C62520636 @default.

• next