Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315498971> ?p ?o ?g. }
- W4315498971 endingPage "330" @default.
- W4315498971 startingPage "319" @default.
- W4315498971 abstract "Abstract With the development of intelligent agents pursuing humanisation, artificial intelligence must consider emotion, the most basic spiritual need in human interaction. Traditional emotional dialogue systems usually use an external emotional dictionary to select appropriate emotional words to add to the response or concatenate emotional tags and semantic features in the decoding step to generate appropriate responses. However, selecting emotional words from a fixed emotional dictionary may result in loss of the diversity and consistency of the response. We propose a semantic and emotion‐based dual latent variable generation model (Dual‐LVG) for dialogue systems, which is able to generate appropriate emotional responses without an emotional dictionary. Different from previous work, the conditional variational autoencoder (CVAE) adopts the standard transformer structure. Then, Dual‐LVG regularises the CVAE latent space by introducing a dual latent space of semantics and emotion. The content diversity and emotional accuracy of the generated responses are improved by learning emotion and semantic features respectively. Moreover, the average attention mechanism is adopted to better extract semantic features at the sequence level, and the semi‐supervised attention mechanism is used in the decoding step to strengthen the fusion of emotional features of the model. Experimental results show that Dual‐LVG can successfully achieve the effect of generating different content by controlling emotional factors." @default.
- W4315498971 created "2023-01-11" @default.
- W4315498971 creator A5003642180 @default.
- W4315498971 creator A5008072409 @default.
- W4315498971 creator A5018952933 @default.
- W4315498971 creator A5026136257 @default.
- W4315498971 creator A5089718306 @default.
- W4315498971 date "2023-01-10" @default.
- W4315498971 modified "2023-10-17" @default.
- W4315498971 title "A semantic and emotion‐based dual latent variable generation model for a dialogue system" @default.
- W4315498971 cites W2581637843 @default.
- W4315498971 cites W2891744372 @default.
- W4315498971 cites W2939308327 @default.
- W4315498971 cites W2952088495 @default.
- W4315498971 cites W2962717182 @default.
- W4315498971 cites W2962796276 @default.
- W4315498971 cites W2963188990 @default.
- W4315498971 cites W2963223306 @default.
- W4315498971 cites W2963797754 @default.
- W4315498971 cites W2964669873 @default.
- W4315498971 cites W2973935944 @default.
- W4315498971 cites W2987787977 @default.
- W4315498971 cites W2996843693 @default.
- W4315498971 cites W3022187094 @default.
- W4315498971 cites W3035451444 @default.
- W4315498971 cites W3098708719 @default.
- W4315498971 cites W3134356777 @default.
- W4315498971 cites W3139432614 @default.
- W4315498971 cites W3155511279 @default.
- W4315498971 cites W3156590455 @default.
- W4315498971 cites W3162128880 @default.
- W4315498971 cites W3211570179 @default.
- W4315498971 cites W4200112965 @default.
- W4315498971 doi "https://doi.org/10.1049/cit2.12153" @default.
- W4315498971 hasPublicationYear "2023" @default.
- W4315498971 type Work @default.
- W4315498971 citedByCount "16" @default.
- W4315498971 countsByYear W43154989712023 @default.
- W4315498971 crossrefType "journal-article" @default.
- W4315498971 hasAuthorship W4315498971A5003642180 @default.
- W4315498971 hasAuthorship W4315498971A5008072409 @default.
- W4315498971 hasAuthorship W4315498971A5018952933 @default.
- W4315498971 hasAuthorship W4315498971A5026136257 @default.
- W4315498971 hasAuthorship W4315498971A5089718306 @default.
- W4315498971 hasBestOaLocation W43154989711 @default.
- W4315498971 hasConcept C101738243 @default.
- W4315498971 hasConcept C108583219 @default.
- W4315498971 hasConcept C112933361 @default.
- W4315498971 hasConcept C11413529 @default.
- W4315498971 hasConcept C138885662 @default.
- W4315498971 hasConcept C154945302 @default.
- W4315498971 hasConcept C15744967 @default.
- W4315498971 hasConcept C170133592 @default.
- W4315498971 hasConcept C174107131 @default.
- W4315498971 hasConcept C180747234 @default.
- W4315498971 hasConcept C184337299 @default.
- W4315498971 hasConcept C199360897 @default.
- W4315498971 hasConcept C204321447 @default.
- W4315498971 hasConcept C2780980858 @default.
- W4315498971 hasConcept C41008148 @default.
- W4315498971 hasConcept C41895202 @default.
- W4315498971 hasConcept C51167844 @default.
- W4315498971 hasConcept C57273362 @default.
- W4315498971 hasConcept C77805123 @default.
- W4315498971 hasConceptScore W4315498971C101738243 @default.
- W4315498971 hasConceptScore W4315498971C108583219 @default.
- W4315498971 hasConceptScore W4315498971C112933361 @default.
- W4315498971 hasConceptScore W4315498971C11413529 @default.
- W4315498971 hasConceptScore W4315498971C138885662 @default.
- W4315498971 hasConceptScore W4315498971C154945302 @default.
- W4315498971 hasConceptScore W4315498971C15744967 @default.
- W4315498971 hasConceptScore W4315498971C170133592 @default.
- W4315498971 hasConceptScore W4315498971C174107131 @default.
- W4315498971 hasConceptScore W4315498971C180747234 @default.
- W4315498971 hasConceptScore W4315498971C184337299 @default.
- W4315498971 hasConceptScore W4315498971C199360897 @default.
- W4315498971 hasConceptScore W4315498971C204321447 @default.
- W4315498971 hasConceptScore W4315498971C2780980858 @default.
- W4315498971 hasConceptScore W4315498971C41008148 @default.
- W4315498971 hasConceptScore W4315498971C41895202 @default.
- W4315498971 hasConceptScore W4315498971C51167844 @default.
- W4315498971 hasConceptScore W4315498971C57273362 @default.
- W4315498971 hasConceptScore W4315498971C77805123 @default.
- W4315498971 hasFunder F4320321001 @default.
- W4315498971 hasIssue "2" @default.
- W4315498971 hasLocation W43154989711 @default.
- W4315498971 hasOpenAccess W4315498971 @default.
- W4315498971 hasPrimaryLocation W43154989711 @default.
- W4315498971 hasRelatedWork W1971784869 @default.
- W4315498971 hasRelatedWork W2018025176 @default.
- W4315498971 hasRelatedWork W2124251782 @default.
- W4315498971 hasRelatedWork W2133829462 @default.
- W4315498971 hasRelatedWork W2152544583 @default.
- W4315498971 hasRelatedWork W2588002110 @default.
- W4315498971 hasRelatedWork W3018295854 @default.
- W4315498971 hasRelatedWork W4308618235 @default.
- W4315498971 hasRelatedWork W4385572821 @default.
- W4315498971 hasRelatedWork W85598974 @default.