Matches in SemOpenAlex for { <https://semopenalex.org/work/W2783737271> ?p ?o ?g. }
- W2783737271 abstract "In practice, most spoken language understanding systems process user input in a pipelined manner; first domain is predicted, then intent and semantic slots are inferred according to the semantic frames of the predicted domain. The pipeline approach, however, has some disadvantages: error propagation and lack of information sharing. To address these issues, we present a unified neural network that jointly performs domain, intent, and slot predictions. Our approach adopts a principled architecture for multitask learning to fold in the state-of-the-art models for each task. With a few more ingredients, e.g. orthography-sensitive input encoding and curriculum training, our model delivered significant improvements in all three tasks across all domains over strong baselines, including one using oracle prediction for domain detection, on real user data of a commercial personal assistant." @default.
- W2783737271 created "2018-01-26" @default.
- W2783737271 creator A5010305620 @default.
- W2783737271 creator A5059051692 @default.
- W2783737271 creator A5061235567 @default.
- W2783737271 date "2018-01-16" @default.
- W2783737271 modified "2023-09-23" @default.
- W2783737271 title "OneNet: Joint Domain, Intent, Slot Prediction for Spoken Language Understanding" @default.
- W2783737271 cites W2094472029 @default.
- W2783737271 cites W2117130368 @default.
- W2783737271 cites W2131774270 @default.
- W2783737271 cites W2251816562 @default.
- W2783737271 cites W2295800284 @default.
- W2783737271 cites W2296283641 @default.
- W2783737271 cites W2313437166 @default.
- W2783737271 cites W2513629222 @default.
- W2783737271 cites W2514158504 @default.
- W2783737271 cites W2534870421 @default.
- W2783737271 cites W2540485556 @default.
- W2783737271 cites W2562335618 @default.
- W2783737271 cites W2577255746 @default.
- W2783737271 cites W2741239878 @default.
- W2783737271 cites W2742039423 @default.
- W2783737271 cites W2950577311 @default.
- W2783737271 cites W2963974889 @default.
- W2783737271 cites W2964121744 @default.
- W2783737271 doi "https://doi.org/10.48550/arxiv.1801.05149" @default.
- W2783737271 hasPublicationYear "2018" @default.
- W2783737271 type Work @default.
- W2783737271 sameAs 2783737271 @default.
- W2783737271 citedByCount "0" @default.
- W2783737271 crossrefType "posted-content" @default.
- W2783737271 hasAuthorship W2783737271A5010305620 @default.
- W2783737271 hasAuthorship W2783737271A5059051692 @default.
- W2783737271 hasAuthorship W2783737271A5061235567 @default.
- W2783737271 hasBestOaLocation W27837372711 @default.
- W2783737271 hasConcept C105795698 @default.
- W2783737271 hasConcept C119857082 @default.
- W2783737271 hasConcept C125411270 @default.
- W2783737271 hasConcept C127413603 @default.
- W2783737271 hasConcept C134306372 @default.
- W2783737271 hasConcept C138885662 @default.
- W2783737271 hasConcept C150670947 @default.
- W2783737271 hasConcept C154945302 @default.
- W2783737271 hasConcept C162324750 @default.
- W2783737271 hasConcept C165064840 @default.
- W2783737271 hasConcept C170154142 @default.
- W2783737271 hasConcept C18555067 @default.
- W2783737271 hasConcept C187736073 @default.
- W2783737271 hasConcept C199360897 @default.
- W2783737271 hasConcept C204321447 @default.
- W2783737271 hasConcept C2776230583 @default.
- W2783737271 hasConcept C2780451532 @default.
- W2783737271 hasConcept C28490314 @default.
- W2783737271 hasConcept C33923547 @default.
- W2783737271 hasConcept C36503486 @default.
- W2783737271 hasConcept C41008148 @default.
- W2783737271 hasConcept C41895202 @default.
- W2783737271 hasConcept C43521106 @default.
- W2783737271 hasConcept C50644808 @default.
- W2783737271 hasConcept C55166926 @default.
- W2783737271 hasConcept C554936623 @default.
- W2783737271 hasConcept C98045186 @default.
- W2783737271 hasConceptScore W2783737271C105795698 @default.
- W2783737271 hasConceptScore W2783737271C119857082 @default.
- W2783737271 hasConceptScore W2783737271C125411270 @default.
- W2783737271 hasConceptScore W2783737271C127413603 @default.
- W2783737271 hasConceptScore W2783737271C134306372 @default.
- W2783737271 hasConceptScore W2783737271C138885662 @default.
- W2783737271 hasConceptScore W2783737271C150670947 @default.
- W2783737271 hasConceptScore W2783737271C154945302 @default.
- W2783737271 hasConceptScore W2783737271C162324750 @default.
- W2783737271 hasConceptScore W2783737271C165064840 @default.
- W2783737271 hasConceptScore W2783737271C170154142 @default.
- W2783737271 hasConceptScore W2783737271C18555067 @default.
- W2783737271 hasConceptScore W2783737271C187736073 @default.
- W2783737271 hasConceptScore W2783737271C199360897 @default.
- W2783737271 hasConceptScore W2783737271C204321447 @default.
- W2783737271 hasConceptScore W2783737271C2776230583 @default.
- W2783737271 hasConceptScore W2783737271C2780451532 @default.
- W2783737271 hasConceptScore W2783737271C28490314 @default.
- W2783737271 hasConceptScore W2783737271C33923547 @default.
- W2783737271 hasConceptScore W2783737271C36503486 @default.
- W2783737271 hasConceptScore W2783737271C41008148 @default.
- W2783737271 hasConceptScore W2783737271C41895202 @default.
- W2783737271 hasConceptScore W2783737271C43521106 @default.
- W2783737271 hasConceptScore W2783737271C50644808 @default.
- W2783737271 hasConceptScore W2783737271C55166926 @default.
- W2783737271 hasConceptScore W2783737271C554936623 @default.
- W2783737271 hasConceptScore W2783737271C98045186 @default.
- W2783737271 hasLocation W27837372711 @default.
- W2783737271 hasOpenAccess W2783737271 @default.
- W2783737271 hasPrimaryLocation W27837372711 @default.
- W2783737271 hasRelatedWork W2015950787 @default.
- W2783737271 hasRelatedWork W2020540721 @default.
- W2783737271 hasRelatedWork W2374451721 @default.
- W2783737271 hasRelatedWork W2391431582 @default.
- W2783737271 hasRelatedWork W2474469336 @default.
- W2783737271 hasRelatedWork W2578916128 @default.
- W2783737271 hasRelatedWork W2961085424 @default.