Matches in SemOpenAlex for { <https://semopenalex.org/work/W2962715022> ?p ?o ?g. }
- W2962715022 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.
- W2962715022 created "2019-07-30" @default.
- W2962715022 creator A5010305620 @default.
- W2962715022 creator A5059051692 @default.
- W2962715022 creator A5061235567 @default.
- W2962715022 date "2017-12-01" @default.
- W2962715022 modified "2023-09-25" @default.
- W2962715022 title "ONENET: Joint domain, intent, slot prediction for spoken language understanding" @default.
- W2962715022 cites W1971034924 @default.
- W2962715022 cites W1986147089 @default.
- W2962715022 cites W2010152689 @default.
- W2962715022 cites W2064675550 @default.
- W2962715022 cites W2094472029 @default.
- W2962715022 cites W2117130368 @default.
- W2962715022 cites W2131774270 @default.
- W2962715022 cites W2251249950 @default.
- W2962715022 cites W2251816562 @default.
- W2962715022 cites W2252070015 @default.
- W2962715022 cites W2295800284 @default.
- W2962715022 cites W2514158504 @default.
- W2962715022 cites W2529478425 @default.
- W2962715022 cites W2562335618 @default.
- W2962715022 cites W2632474040 @default.
- W2962715022 cites W2741239878 @default.
- W2962715022 cites W2742039423 @default.
- W2962715022 cites W2963050422 @default.
- W2962715022 cites W2963974889 @default.
- W2962715022 cites W4249179470 @default.
- W2962715022 doi "https://doi.org/10.1109/asru.2017.8268984" @default.
- W2962715022 hasPublicationYear "2017" @default.
- W2962715022 type Work @default.
- W2962715022 sameAs 2962715022 @default.
- W2962715022 citedByCount "67" @default.
- W2962715022 countsByYear W29627150222018 @default.
- W2962715022 countsByYear W29627150222019 @default.
- W2962715022 countsByYear W29627150222020 @default.
- W2962715022 countsByYear W29627150222021 @default.
- W2962715022 countsByYear W29627150222022 @default.
- W2962715022 crossrefType "proceedings-article" @default.
- W2962715022 hasAuthorship W2962715022A5010305620 @default.
- W2962715022 hasAuthorship W2962715022A5059051692 @default.
- W2962715022 hasAuthorship W2962715022A5061235567 @default.
- W2962715022 hasBestOaLocation W29627150222 @default.
- W2962715022 hasConcept C125411270 @default.
- W2962715022 hasConcept C127413603 @default.
- W2962715022 hasConcept C134306372 @default.
- W2962715022 hasConcept C137293760 @default.
- W2962715022 hasConcept C150670947 @default.
- W2962715022 hasConcept C154945302 @default.
- W2962715022 hasConcept C162324750 @default.
- W2962715022 hasConcept C170154142 @default.
- W2962715022 hasConcept C17744445 @default.
- W2962715022 hasConcept C18555067 @default.
- W2962715022 hasConcept C187736073 @default.
- W2962715022 hasConcept C199360897 @default.
- W2962715022 hasConcept C199539241 @default.
- W2962715022 hasConcept C204321447 @default.
- W2962715022 hasConcept C2776230583 @default.
- W2962715022 hasConcept C2780451532 @default.
- W2962715022 hasConcept C33923547 @default.
- W2962715022 hasConcept C36503486 @default.
- W2962715022 hasConcept C41008148 @default.
- W2962715022 hasConcept C43521106 @default.
- W2962715022 hasConcept C50644808 @default.
- W2962715022 hasConcept C55166926 @default.
- W2962715022 hasConcept C554936623 @default.
- W2962715022 hasConceptScore W2962715022C125411270 @default.
- W2962715022 hasConceptScore W2962715022C127413603 @default.
- W2962715022 hasConceptScore W2962715022C134306372 @default.
- W2962715022 hasConceptScore W2962715022C137293760 @default.
- W2962715022 hasConceptScore W2962715022C150670947 @default.
- W2962715022 hasConceptScore W2962715022C154945302 @default.
- W2962715022 hasConceptScore W2962715022C162324750 @default.
- W2962715022 hasConceptScore W2962715022C170154142 @default.
- W2962715022 hasConceptScore W2962715022C17744445 @default.
- W2962715022 hasConceptScore W2962715022C18555067 @default.
- W2962715022 hasConceptScore W2962715022C187736073 @default.
- W2962715022 hasConceptScore W2962715022C199360897 @default.
- W2962715022 hasConceptScore W2962715022C199539241 @default.
- W2962715022 hasConceptScore W2962715022C204321447 @default.
- W2962715022 hasConceptScore W2962715022C2776230583 @default.
- W2962715022 hasConceptScore W2962715022C2780451532 @default.
- W2962715022 hasConceptScore W2962715022C33923547 @default.
- W2962715022 hasConceptScore W2962715022C36503486 @default.
- W2962715022 hasConceptScore W2962715022C41008148 @default.
- W2962715022 hasConceptScore W2962715022C43521106 @default.
- W2962715022 hasConceptScore W2962715022C50644808 @default.
- W2962715022 hasConceptScore W2962715022C55166926 @default.
- W2962715022 hasConceptScore W2962715022C554936623 @default.
- W2962715022 hasLocation W29627150221 @default.
- W2962715022 hasLocation W29627150222 @default.
- W2962715022 hasOpenAccess W2962715022 @default.
- W2962715022 hasPrimaryLocation W29627150221 @default.
- W2962715022 hasRelatedWork W2015950787 @default.
- W2962715022 hasRelatedWork W2020540721 @default.
- W2962715022 hasRelatedWork W2022859009 @default.
- W2962715022 hasRelatedWork W2359001871 @default.
- W2962715022 hasRelatedWork W2578916128 @default.
- W2962715022 hasRelatedWork W3093097038 @default.
- W2962715022 hasRelatedWork W3186676198 @default.