HappyBot: Generating Empathetic Dialogue Responses by Improving User Experience Look-ahead

47 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog (2019, background): “Shin and colleagues uses on-policy learning in conjunction with a user-sentiment approximator to improve a seq2seq model [56], but are unable to learn directly from user feedback.”
Human-centric Dialog Training via Offline Reinforcement Learning (2020, methodology): “Shin et al. (2019) use on-policy learning in conjunction with a user-sentiment approximator to improve a seq2seq model, but are unable to learn directly from user feedback.”
Hierarchical Reinforcement Learning for Open-Domain Dialog (2019, methodology): “Sentiment has been used as a reward in an RL setting for dialog (Shin et al. 2019).”
Understanding and predicting user dissatisfaction in a neural generative chatbot (2021, methodology): “For oneon-one empathetic conversations like ours, Shin et al. (2019) trained a neural generative model with reinforcement learning to improve next-turn user sentiment (as simulated by a user response model, rather than human responses).”
Unsupervised Evaluation of Interactive Dialog with DialoGPT (2020, unknown): “Shin et al. (2019) measure empathy, ﬂuency and relevance.”