Constructing Emotion Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation

TL;DR

This paper introduces Dual-Emp, a dual-generative model that constructs emotion consensus and leverages unpaired data to improve empathetic dialogue generation, addressing data scarcity and bidirectional emotion flow.

Contribution

The paper proposes a novel dual-generative framework that models emotion consensus and utilizes unpaired data for more effective empathetic dialogue generation.

Findings

Outperforms baselines in automatic evaluations

Generates more coherent empathetic responses

Effectively leverages unpaired data for training

Abstract

Researches on dialogue empathy aim to endow an agent with the capacity of accurate understanding and proper responding for emotions. Existing models for empathetic dialogue generation focus on the emotion flow in one direction, that is, from the context to response. We argue that conducting an empathetic conversation is a bidirectional process, where empathy occurs when the emotions of two interlocutors could converge on the same point, i.e., reaching an emotion consensus. Besides, we also find that the empathetic dialogue corpus is extremely limited, which further restricts the model performance. To address the above issues, we propose a dual-generative model, Dual-Emp, to simultaneously construct the emotion consensus and utilize some external unpaired data. Specifically, our model integrates a forward dialogue model, a backward dialogue model, and a discrete latent variable representing the emotion consensus into a unified architecture. Then, to alleviate the constraint of paired data, we extract unpaired emotional data from open-domain conversations and employ Dual-Emp to produce pseudo paired empathetic samples, which is more efficient and low-cost than the human annotation. Automatic and human evaluations demonstrate that our method outperforms competitive baselines in producing coherent and empathetic responses.