Generating Empathetic Responses by Looking Ahead the User's Sentiment
This addresses the challenge of empathetic conversation for AI systems, offering a novel perspective that could improve human-machine interactions, though it is incremental in building on existing neural models.
The paper tackled the problem of generating empathetic responses in conversations by modeling the future user emotional state, proposing Sentiment Look-ahead as a reward function in reinforcement learning. The result showed that this approach generated significantly more empathetic, relevant, and fluent responses compared to baselines like multitask learning.
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.