Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896439639> ?p ?o ?g. }
- W2896439639 abstract "Recognising dialogue acts (DA) is important for many natural language processing tasks such as dialogue generation and intention recognition. In this paper, we propose a dual-attention hierarchical recurrent neural network for DA classification. Our model is partially inspired by the observation that conversational utterances are normally associated with both a DA and a topic, where the former captures the social act and the latter describes the subject matter. However, such a dependency between DAs and topics has not been utilised by most existing systems for DA classification. With a novel dual task-specific attention mechanism, our model is able, for utterances, to capture information about both DAs and topics, as well as information about the interactions between them. Experimental results show that by modelling topic as an auxiliary task, our model can significantly improve DA classification, yielding better or comparable performance to the state-of-the-art method on three public datasets." @default.
- W2896439639 created "2018-10-26" @default.
- W2896439639 creator A5022797200 @default.
- W2896439639 creator A5024599321 @default.
- W2896439639 creator A5035339773 @default.
- W2896439639 creator A5040687567 @default.
- W2896439639 creator A5082766959 @default.
- W2896439639 date "2018-10-22" @default.
- W2896439639 modified "2023-10-16" @default.
- W2896439639 title "A Dual-Attention Hierarchical Recurrent Neural Network for Dialogue Act Classification" @default.
- W2896439639 cites W1503312748 @default.
- W2896439639 cites W150462035 @default.
- W2896439639 cites W1542146969 @default.
- W2896439639 cites W1591607137 @default.
- W2896439639 cites W1880262756 @default.
- W2896439639 cites W192515608 @default.
- W2896439639 cites W1991133427 @default.
- W2896439639 cites W2008689742 @default.
- W2896439639 cites W2016589492 @default.
- W2896439639 cites W2038043464 @default.
- W2896439639 cites W2095705004 @default.
- W2896439639 cites W2128970689 @default.
- W2896439639 cites W2129264276 @default.
- W2896439639 cites W2146785422 @default.
- W2896439639 cites W2148830595 @default.
- W2896439639 cites W2167212741 @default.
- W2896439639 cites W2171986392 @default.
- W2896439639 cites W2250539671 @default.
- W2896439639 cites W2252245646 @default.
- W2896439639 cites W2312383716 @default.
- W2896439639 cites W2573626026 @default.
- W2896439639 cites W2615702746 @default.
- W2896439639 cites W2624871570 @default.
- W2896439639 cites W2741675028 @default.
- W2896439639 cites W2756420200 @default.
- W2896439639 cites W2757599232 @default.
- W2896439639 cites W2803437449 @default.
- W2896439639 cites W2884240866 @default.
- W2896439639 cites W2962902328 @default.
- W2896439639 cites W2963544536 @default.
- W2896439639 cites W2963550483 @default.
- W2896439639 cites W2963765493 @default.
- W2896439639 cites W2964036636 @default.
- W2896439639 cites W2964089584 @default.
- W2896439639 cites W2964106094 @default.
- W2896439639 cites W2964121744 @default.
- W2896439639 cites W2964199361 @default.
- W2896439639 cites W2964308564 @default.
- W2896439639 cites W2964331270 @default.
- W2896439639 cites W783082550 @default.
- W2896439639 doi "https://doi.org/10.48550/arxiv.1810.09154" @default.
- W2896439639 hasPublicationYear "2018" @default.
- W2896439639 type Work @default.
- W2896439639 sameAs 2896439639 @default.
- W2896439639 citedByCount "2" @default.
- W2896439639 countsByYear W28964396392020 @default.
- W2896439639 countsByYear W28964396392021 @default.
- W2896439639 crossrefType "posted-content" @default.
- W2896439639 hasAuthorship W2896439639A5022797200 @default.
- W2896439639 hasAuthorship W2896439639A5024599321 @default.
- W2896439639 hasAuthorship W2896439639A5035339773 @default.
- W2896439639 hasAuthorship W2896439639A5040687567 @default.
- W2896439639 hasAuthorship W2896439639A5082766959 @default.
- W2896439639 hasBestOaLocation W28964396391 @default.
- W2896439639 hasConcept C111472728 @default.
- W2896439639 hasConcept C119857082 @default.
- W2896439639 hasConcept C138885662 @default.
- W2896439639 hasConcept C147168706 @default.
- W2896439639 hasConcept C154945302 @default.
- W2896439639 hasConcept C161191863 @default.
- W2896439639 hasConcept C162324750 @default.
- W2896439639 hasConcept C187736073 @default.
- W2896439639 hasConcept C19768560 @default.
- W2896439639 hasConcept C204321447 @default.
- W2896439639 hasConcept C2777855551 @default.
- W2896439639 hasConcept C2780451532 @default.
- W2896439639 hasConcept C2780980858 @default.
- W2896439639 hasConcept C41008148 @default.
- W2896439639 hasConcept C41895202 @default.
- W2896439639 hasConcept C50644808 @default.
- W2896439639 hasConcept C89611455 @default.
- W2896439639 hasConceptScore W2896439639C111472728 @default.
- W2896439639 hasConceptScore W2896439639C119857082 @default.
- W2896439639 hasConceptScore W2896439639C138885662 @default.
- W2896439639 hasConceptScore W2896439639C147168706 @default.
- W2896439639 hasConceptScore W2896439639C154945302 @default.
- W2896439639 hasConceptScore W2896439639C161191863 @default.
- W2896439639 hasConceptScore W2896439639C162324750 @default.
- W2896439639 hasConceptScore W2896439639C187736073 @default.
- W2896439639 hasConceptScore W2896439639C19768560 @default.
- W2896439639 hasConceptScore W2896439639C204321447 @default.
- W2896439639 hasConceptScore W2896439639C2777855551 @default.
- W2896439639 hasConceptScore W2896439639C2780451532 @default.
- W2896439639 hasConceptScore W2896439639C2780980858 @default.
- W2896439639 hasConceptScore W2896439639C41008148 @default.
- W2896439639 hasConceptScore W2896439639C41895202 @default.
- W2896439639 hasConceptScore W2896439639C50644808 @default.
- W2896439639 hasConceptScore W2896439639C89611455 @default.
- W2896439639 hasLocation W28964396391 @default.
- W2896439639 hasLocation W28964396392 @default.