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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Persuasion dialogue systems reflect the machine's ability to make strategicmoves beyond verbal communication, and therefore differentiate themselves fromtask-oriented or open-domain dialogue systems and have their own unique values.However, the repetition and inconsistency problems still persist in dialogueresponse generation and could substantially impact user experience and impedethe persuasion outcome. Besides, although reinforcement learning (RL)approaches have achieved big success in strategic tasks such as games, theyrequire a sophisticated user simulator to provide real-time feedback to thedialogue system, which limits the application of RL on persuasion dialogues. Toaddress these issues towards a better persuasion dialogue system, we apply RLto refine a language model baseline without user simulators, and distillsentence-level information about repetition, inconsistency, and task relevancethrough rewards. Moreover, to better accomplish the persuasion task, the modellearns from human demonstration to imitate human persuasion behavior andselects the most persuasive responses. Experiments show that our modeloutperforms previous state-of-the-art dialogue models on both automatic metricsand human evaluation results on a donation persuasion task, and generates morediverse, consistent and persuasive conversations according to the userfeedback.

Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration