Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951222182> ?p ?o ?g. }
- W2951222182 abstract "This paper presents a deep learning architecture for the semantic decoder component of a Statistical Spoken Dialogue System. In a slot-filling dialogue, the semantic decoder predicts the dialogue act and a set of slot-value pairs from a set of n-best hypotheses returned by the Automatic Speech Recognition. Most current models for spoken language understanding assume (i) word-aligned semantic annotations as in sequence taggers and (ii) delexicalisation, or a mapping of input words to domain-specific concepts using heuristics that try to capture morphological variation but that do not scale to other domains nor to language variation (e.g., morphology, synonyms, paraphrasing ). In this work the semantic decoder is trained using unaligned semantic annotations and it uses distributed semantic representation learning to overcome the limitations of explicit delexicalisation. The proposed architecture uses a convolutional neural network for the sentence representation and a long-short term memory network for the context representation. Results are presented for the publicly available DSTC2 corpus and an In-car corpus which is similar to DSTC2 but has a significantly higher word error rate (WER)." @default.
- W2951222182 created "2019-06-27" @default.
- W2951222182 creator A5001036127 @default.
- W2951222182 creator A5019913562 @default.
- W2951222182 creator A5030147577 @default.
- W2951222182 creator A5040922365 @default.
- W2951222182 creator A5051889115 @default.
- W2951222182 creator A5058838995 @default.
- W2951222182 creator A5087009911 @default.
- W2951222182 date "2016-10-13" @default.
- W2951222182 modified "2023-09-26" @default.
- W2951222182 title "Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding" @default.
- W2951222182 cites W1513615006 @default.
- W2951222182 cites W1904365287 @default.
- W2951222182 cites W1964812476 @default.
- W2951222182 cites W2044704181 @default.
- W2951222182 cites W2064675550 @default.
- W2951222182 cites W2120615054 @default.
- W2951222182 cites W2124895976 @default.
- W2951222182 cites W2158899491 @default.
- W2951222182 cites W2189256702 @default.
- W2951222182 cites W2250297846 @default.
- W2951222182 cites W2250539671 @default.
- W2951222182 cites W2251058040 @default.
- W2951222182 cites W2251355666 @default.
- W2951222182 cites W2395389931 @default.
- W2951222182 cites W2400801499 @default.
- W2951222182 cites W2466446175 @default.
- W2951222182 cites W2471178169 @default.
- W2951222182 cites W2949541494 @default.
- W2951222182 hasPublicationYear "2016" @default.
- W2951222182 type Work @default.
- W2951222182 sameAs 2951222182 @default.
- W2951222182 citedByCount "2" @default.
- W2951222182 countsByYear W29512221822019 @default.
- W2951222182 countsByYear W29512221822020 @default.
- W2951222182 crossrefType "posted-content" @default.
- W2951222182 hasAuthorship W2951222182A5001036127 @default.
- W2951222182 hasAuthorship W2951222182A5019913562 @default.
- W2951222182 hasAuthorship W2951222182A5030147577 @default.
- W2951222182 hasAuthorship W2951222182A5040922365 @default.
- W2951222182 hasAuthorship W2951222182A5051889115 @default.
- W2951222182 hasAuthorship W2951222182A5058838995 @default.
- W2951222182 hasAuthorship W2951222182A5087009911 @default.
- W2951222182 hasConcept C111919701 @default.
- W2951222182 hasConcept C127705205 @default.
- W2951222182 hasConcept C137293760 @default.
- W2951222182 hasConcept C138885662 @default.
- W2951222182 hasConcept C151730666 @default.
- W2951222182 hasConcept C154945302 @default.
- W2951222182 hasConcept C173862523 @default.
- W2951222182 hasConcept C177264268 @default.
- W2951222182 hasConcept C199360897 @default.
- W2951222182 hasConcept C204321447 @default.
- W2951222182 hasConcept C2129575 @default.
- W2951222182 hasConcept C2776230583 @default.
- W2951222182 hasConcept C2777530160 @default.
- W2951222182 hasConcept C2779343474 @default.
- W2951222182 hasConcept C28490314 @default.
- W2951222182 hasConcept C40969351 @default.
- W2951222182 hasConcept C41008148 @default.
- W2951222182 hasConcept C41895202 @default.
- W2951222182 hasConcept C511149849 @default.
- W2951222182 hasConcept C6881194 @default.
- W2951222182 hasConcept C81363708 @default.
- W2951222182 hasConcept C86803240 @default.
- W2951222182 hasConcept C90805587 @default.
- W2951222182 hasConceptScore W2951222182C111919701 @default.
- W2951222182 hasConceptScore W2951222182C127705205 @default.
- W2951222182 hasConceptScore W2951222182C137293760 @default.
- W2951222182 hasConceptScore W2951222182C138885662 @default.
- W2951222182 hasConceptScore W2951222182C151730666 @default.
- W2951222182 hasConceptScore W2951222182C154945302 @default.
- W2951222182 hasConceptScore W2951222182C173862523 @default.
- W2951222182 hasConceptScore W2951222182C177264268 @default.
- W2951222182 hasConceptScore W2951222182C199360897 @default.
- W2951222182 hasConceptScore W2951222182C204321447 @default.
- W2951222182 hasConceptScore W2951222182C2129575 @default.
- W2951222182 hasConceptScore W2951222182C2776230583 @default.
- W2951222182 hasConceptScore W2951222182C2777530160 @default.
- W2951222182 hasConceptScore W2951222182C2779343474 @default.
- W2951222182 hasConceptScore W2951222182C28490314 @default.
- W2951222182 hasConceptScore W2951222182C40969351 @default.
- W2951222182 hasConceptScore W2951222182C41008148 @default.
- W2951222182 hasConceptScore W2951222182C41895202 @default.
- W2951222182 hasConceptScore W2951222182C511149849 @default.
- W2951222182 hasConceptScore W2951222182C6881194 @default.
- W2951222182 hasConceptScore W2951222182C81363708 @default.
- W2951222182 hasConceptScore W2951222182C86803240 @default.
- W2951222182 hasConceptScore W2951222182C90805587 @default.
- W2951222182 hasLocation W29512221821 @default.
- W2951222182 hasOpenAccess W2951222182 @default.
- W2951222182 hasPrimaryLocation W29512221821 @default.
- W2951222182 hasRelatedWork W2064675550 @default.
- W2951222182 hasRelatedWork W2079264965 @default.
- W2951222182 hasRelatedWork W2223628738 @default.
- W2951222182 hasRelatedWork W2247305181 @default.
- W2951222182 hasRelatedWork W2534381863 @default.
- W2951222182 hasRelatedWork W2579200852 @default.
- W2951222182 hasRelatedWork W2798308429 @default.