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 is a crucial factor in open-domain conversations, which naturallyshows one's caring and understanding to others. Though several methods havebeen proposed to generate empathetic responses, existing works often lead tomonotonous empathy that refers to generic and safe expressions. In this paper,we propose to use explicit control to guide the empathy expression and design aframework DiffusEmp based on conditional diffusion language model to unify theutilization of dialogue context and attribute-oriented control signals.Specifically, communication mechanism, intent, and semantic frame are importedas multi-grained signals that control the empathy realization from coarse tofine levels. We then design a specific masking strategy to reflect therelationship between multi-grained signals and response tokens, and integrateit into the diffusion model to influence the generative process. Experimentalresults on a benchmark dataset EmpatheticDialogue show that our frameworkoutperforms competitive baselines in terms of controllability, informativeness,and diversity without the loss of context-relatedness.

DiffusEmp: A Diffusion Model-Based Framework with Multi-Grained Control for Empathetic Response Generation