English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Empathy, which is widely used in psychological counselling, is a key trait ofeveryday human conversations. Equipped with commonsense knowledge, currentapproaches to empathetic response generation focus on capturing implicitemotion within dialogue context, where the emotions are treated as a staticvariable throughout the conversations. However, emotions change dynamicallybetween utterances, which makes previous works difficult to perceive theemotion flow and predict the correct emotion of the target response, leading toinappropriate response. Furthermore, simply importing commonsense knowledgewithout harmonization may trigger the conflicts between knowledge and emotion,which confuse the model to choose incorrect information to guide the generationprocess. To address the above problems, we propose a Serial Encoding andEmotion-Knowledge interaction (SEEK) method for empathetic dialogue generation.We use a fine-grained encoding strategy which is more sensitive to the emotiondynamics (emotion flow) in the conversations to predict the emotion-intentcharacteristic of response. Besides, we design a novel framework to model theinteraction between knowledge and emotion to generate more sensible response.Extensive experiments on EmpatheticDialogues demonstrate that SEEK outperformsthe strong baselines in both automatic and manual evaluations.

Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection