Matches in SemOpenAlex for { <https://semopenalex.org/work/W3176162574> ?p ?o ?g. }
- W3176162574 endingPage "77190" @default.
- W3176162574 startingPage "77176" @default.
- W3176162574 abstract "Empathy is fundamental to humans amongst other animals. It is key to strong social cohesion, cornerstone of health and success of societies. Thus, empathy could be an important component of effective human-computer interactions through conversations. This has motivated a whole sub-field of research focused on empathetic response generation. The majority of existing methods for empathetic response generation rely on the emotion of the context to generate empathetic responses. However, empathy is much more than generating responses with an appropriate emotion. It also often entails subtle expressions of understanding and personal resonance with the situation of the other interlocutor. Unfortunately, such qualities are difficult to quantify, and the datasets lack the relevant annotations. To address this issue, in this paper we propose an approach that relies on exemplars to cue the generative model on fine stylistic properties that signal empathy to the interlocutor. To this end, we employ dense passage retrieval to extract relevant exemplary responses from the training set. Three elements of human communication—emotional presence, interpretation, and exploration—and sentiment are additionally introduced using synthetic labels to guide the generation towards empathy. The human evaluation is also extended by these elements of human communication. We empirically show that these approaches yield significant improvements in empathetic response quality in terms of both automated and human-evaluated metrics. The implementation is available at https://github.com/declare-lab/exemplary-empathy." @default.
- W3176162574 created "2021-07-05" @default.
- W3176162574 creator A5007003459 @default.
- W3176162574 creator A5033376109 @default.
- W3176162574 creator A5049701126 @default.
- W3176162574 creator A5074760783 @default.
- W3176162574 creator A5082450455 @default.
- W3176162574 creator A5086877005 @default.
- W3176162574 date "2022-01-01" @default.
- W3176162574 modified "2023-10-18" @default.
- W3176162574 title "Exemplars-Guided Empathetic Response Generation Controlled by the Elements of Human Communication" @default.
- W3176162574 cites W1531773291 @default.
- W3176162574 cites W1806806209 @default.
- W3176162574 cites W1902237438 @default.
- W3176162574 cites W2018621954 @default.
- W3176162574 cites W2101105183 @default.
- W3176162574 cites W2147093380 @default.
- W3176162574 cites W2250539671 @default.
- W3176162574 cites W2465954854 @default.
- W3176162574 cites W2565875961 @default.
- W3176162574 cites W2808437126 @default.
- W3176162574 cites W2885421725 @default.
- W3176162574 cites W2889969789 @default.
- W3176162574 cites W2912924812 @default.
- W3176162574 cites W2915188050 @default.
- W3176162574 cites W2947683321 @default.
- W3176162574 cites W2951583236 @default.
- W3176162574 cites W2963018920 @default.
- W3176162574 cites W2963188990 @default.
- W3176162574 cites W2963206148 @default.
- W3176162574 cites W2963521540 @default.
- W3176162574 cites W2963825865 @default.
- W3176162574 cites W2963925437 @default.
- W3176162574 cites W2970303069 @default.
- W3176162574 cites W2997679291 @default.
- W3176162574 cites W3034531294 @default.
- W3176162574 cites W3035387782 @default.
- W3176162574 cites W3040809437 @default.
- W3176162574 cites W3099700870 @default.
- W3176162574 cites W3104982372 @default.
- W3176162574 cites W3105906861 @default.
- W3176162574 cites W3116376974 @default.
- W3176162574 cites W3154272574 @default.
- W3176162574 cites W3155807546 @default.
- W3176162574 cites W4234193032 @default.
- W3176162574 cites W4239988189 @default.
- W3176162574 doi "https://doi.org/10.1109/access.2022.3193159" @default.
- W3176162574 hasPublicationYear "2022" @default.
- W3176162574 type Work @default.
- W3176162574 sameAs 3176162574 @default.
- W3176162574 citedByCount "4" @default.
- W3176162574 countsByYear W31761625742021 @default.
- W3176162574 countsByYear W31761625742023 @default.
- W3176162574 crossrefType "journal-article" @default.
- W3176162574 hasAuthorship W3176162574A5007003459 @default.
- W3176162574 hasAuthorship W3176162574A5033376109 @default.
- W3176162574 hasAuthorship W3176162574A5049701126 @default.
- W3176162574 hasAuthorship W3176162574A5074760783 @default.
- W3176162574 hasAuthorship W3176162574A5082450455 @default.
- W3176162574 hasAuthorship W3176162574A5086877005 @default.
- W3176162574 hasBestOaLocation W31761625741 @default.
- W3176162574 hasConcept C121332964 @default.
- W3176162574 hasConcept C151730666 @default.
- W3176162574 hasConcept C154945302 @default.
- W3176162574 hasConcept C15744967 @default.
- W3176162574 hasConcept C168167062 @default.
- W3176162574 hasConcept C177264268 @default.
- W3176162574 hasConcept C180747234 @default.
- W3176162574 hasConcept C199360897 @default.
- W3176162574 hasConcept C2779343474 @default.
- W3176162574 hasConcept C2779885105 @default.
- W3176162574 hasConcept C30539005 @default.
- W3176162574 hasConcept C39890363 @default.
- W3176162574 hasConcept C41008148 @default.
- W3176162574 hasConcept C46312422 @default.
- W3176162574 hasConcept C77805123 @default.
- W3176162574 hasConcept C86803240 @default.
- W3176162574 hasConcept C97355855 @default.
- W3176162574 hasConceptScore W3176162574C121332964 @default.
- W3176162574 hasConceptScore W3176162574C151730666 @default.
- W3176162574 hasConceptScore W3176162574C154945302 @default.
- W3176162574 hasConceptScore W3176162574C15744967 @default.
- W3176162574 hasConceptScore W3176162574C168167062 @default.
- W3176162574 hasConceptScore W3176162574C177264268 @default.
- W3176162574 hasConceptScore W3176162574C180747234 @default.
- W3176162574 hasConceptScore W3176162574C199360897 @default.
- W3176162574 hasConceptScore W3176162574C2779343474 @default.
- W3176162574 hasConceptScore W3176162574C2779885105 @default.
- W3176162574 hasConceptScore W3176162574C30539005 @default.
- W3176162574 hasConceptScore W3176162574C39890363 @default.
- W3176162574 hasConceptScore W3176162574C41008148 @default.
- W3176162574 hasConceptScore W3176162574C46312422 @default.
- W3176162574 hasConceptScore W3176162574C77805123 @default.
- W3176162574 hasConceptScore W3176162574C86803240 @default.
- W3176162574 hasConceptScore W3176162574C97355855 @default.
- W3176162574 hasFunder F4320320751 @default.
- W3176162574 hasFunder F4320321739 @default.
- W3176162574 hasFunder F4320324201 @default.