pith. sign in

arxiv: 1906.08487 · v3 · pith:F3A2EC3Ynew · submitted 2019-06-20 · 💻 cs.CL · cs.AI

Generating Empathetic Responses by Looking Ahead the User's Sentiment

classification 💻 cs.CL cs.AI
keywords usersentimentempatheticlook-aheadresponsesconversationemotionemotional
0
0 comments X
read the original abstract

An important aspect of human conversation difficult for machines is conversing with empathy, which is to understand the user's emotion and respond appropriately. Recent neural conversation models that attempted to generate empathetic responses either focused on conditioning the output to a given emotion, or incorporating the current user emotional state. However, these approaches do not factor in how the user would feel towards the generated response. Hence, in this paper, we propose Sentiment Look-ahead, which is a novel perspective for empathy that models the future user emotional state. In short, Sentiment Look-ahead is a reward function under a reinforcement learning framework that provides a higher reward to the generative model when the generated utterance improves the user's sentiment. We implement and evaluate three different possible implementations of sentiment look-ahead and empirically show that our proposed approach can generate significantly more empathetic, relevant, and fluent responses than other competitive baselines such as multitask learning.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog

    cs.LG 2019-06 unverdicted novelty 6.0

    Develops Way Off-Policy batch RL algorithms with pre-trained model priors, KL-control, and dropout uncertainty estimates to learn implicit rewards from offline human dialog data, reporting live deployment gains over p...