Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311759250> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4311759250 endingPage "83" @default.
- W4311759250 startingPage "77" @default.
- W4311759250 abstract "Dialog act recognition (DAR) and sentiment classification (SC) are two correlative tasks to capture speakers’ intentions, where dialog act and sentiment can indicate the explicit and the implicit intentions separately. Current state-of-the-art methods usually leverage the graph neural networks or attention mechanism to capture the contextual dependency of an utterance, thereby aiding in efficient identification of the speakers’ intentions. Although existing attention mechanisms can automatically obtain the corresponding coefficient of each utterance based on the utterance-level embeddings, they often ignore the reliability of the utterance-level embeddings. This promotes us to propose an ensemble model with two-stage learning for joint DAR and SC. Firstly, we employ the BiLSTM as the encoder to capture the features of utterances, which are referred to “confidence vector” of the utterance-level embedding. Further, we introduce an edge-aware graph attention network to improve the classifier’s performance by using the confidence vector to selectively leverage the contextual information. Experimental results on two benchmark datasets show that our framework obtains state-of-the-art performances against all baselines, demonstrating the effectiveness of our method." @default.
- W4311759250 created "2022-12-28" @default.
- W4311759250 creator A5020993341 @default.
- W4311759250 creator A5042575695 @default.
- W4311759250 creator A5062675104 @default.
- W4311759250 creator A5081346568 @default.
- W4311759250 creator A5087772007 @default.
- W4311759250 date "2023-01-01" @default.
- W4311759250 modified "2023-10-14" @default.
- W4311759250 title "A novel ensemble model with two-stage learning for joint dialog act recognition and sentiment classification" @default.
- W4311759250 cites W1985053113 @default.
- W4311759250 cites W2064675550 @default.
- W4311759250 cites W2065926058 @default.
- W4311759250 cites W2088670588 @default.
- W4311759250 cites W2135557329 @default.
- W4311759250 cites W2767645833 @default.
- W4311759250 cites W2963873807 @default.
- W4311759250 cites W3208152475 @default.
- W4311759250 cites W4221117831 @default.
- W4311759250 cites W4224026172 @default.
- W4311759250 cites W4225484863 @default.
- W4311759250 cites W4286511258 @default.
- W4311759250 cites W4291824696 @default.
- W4311759250 cites W4307900381 @default.
- W4311759250 doi "https://doi.org/10.1016/j.patrec.2022.11.032" @default.
- W4311759250 hasPublicationYear "2023" @default.
- W4311759250 type Work @default.
- W4311759250 citedByCount "3" @default.
- W4311759250 countsByYear W43117592502023 @default.
- W4311759250 crossrefType "journal-article" @default.
- W4311759250 hasAuthorship W4311759250A5020993341 @default.
- W4311759250 hasAuthorship W4311759250A5042575695 @default.
- W4311759250 hasAuthorship W4311759250A5062675104 @default.
- W4311759250 hasAuthorship W4311759250A5081346568 @default.
- W4311759250 hasAuthorship W4311759250A5087772007 @default.
- W4311759250 hasConcept C111919701 @default.
- W4311759250 hasConcept C118505674 @default.
- W4311759250 hasConcept C119857082 @default.
- W4311759250 hasConcept C136764020 @default.
- W4311759250 hasConcept C153083717 @default.
- W4311759250 hasConcept C153180895 @default.
- W4311759250 hasConcept C154945302 @default.
- W4311759250 hasConcept C173853756 @default.
- W4311759250 hasConcept C204321447 @default.
- W4311759250 hasConcept C2775852435 @default.
- W4311759250 hasConcept C28490314 @default.
- W4311759250 hasConcept C41008148 @default.
- W4311759250 hasConcept C66402592 @default.
- W4311759250 hasConcept C95623464 @default.
- W4311759250 hasConceptScore W4311759250C111919701 @default.
- W4311759250 hasConceptScore W4311759250C118505674 @default.
- W4311759250 hasConceptScore W4311759250C119857082 @default.
- W4311759250 hasConceptScore W4311759250C136764020 @default.
- W4311759250 hasConceptScore W4311759250C153083717 @default.
- W4311759250 hasConceptScore W4311759250C153180895 @default.
- W4311759250 hasConceptScore W4311759250C154945302 @default.
- W4311759250 hasConceptScore W4311759250C173853756 @default.
- W4311759250 hasConceptScore W4311759250C204321447 @default.
- W4311759250 hasConceptScore W4311759250C2775852435 @default.
- W4311759250 hasConceptScore W4311759250C28490314 @default.
- W4311759250 hasConceptScore W4311759250C41008148 @default.
- W4311759250 hasConceptScore W4311759250C66402592 @default.
- W4311759250 hasConceptScore W4311759250C95623464 @default.
- W4311759250 hasFunder F4320321001 @default.
- W4311759250 hasFunder F4320321543 @default.
- W4311759250 hasFunder F4320336593 @default.
- W4311759250 hasLocation W43117592501 @default.
- W4311759250 hasOpenAccess W4311759250 @default.
- W4311759250 hasPrimaryLocation W43117592501 @default.
- W4311759250 hasRelatedWork W1900635591 @default.
- W4311759250 hasRelatedWork W1973109623 @default.
- W4311759250 hasRelatedWork W2046811668 @default.
- W4311759250 hasRelatedWork W2278256305 @default.
- W4311759250 hasRelatedWork W2563096758 @default.
- W4311759250 hasRelatedWork W3011644728 @default.
- W4311759250 hasRelatedWork W3117273682 @default.
- W4311759250 hasRelatedWork W3192794374 @default.
- W4311759250 hasRelatedWork W4226422436 @default.
- W4311759250 hasRelatedWork W4362613237 @default.
- W4311759250 hasVolume "165" @default.
- W4311759250 isParatext "false" @default.
- W4311759250 isRetracted "false" @default.
- W4311759250 workType "article" @default.