EmpHi: Generating Empathetic Responses with Human-like Intents

TL;DR

EmpHi is a novel model that generates empathetic responses with human-like intents by learning intent distributions, improving empathy, relevance, and diversity in conversational AI.

Contribution

It introduces a discrete latent variable to model empathetic intents, enabling more human-like and diverse empathetic responses in dialogue systems.

Findings

Outperforms state-of-the-art models in empathy, relevance, and diversity

Demonstrates high interpretability and response quality

Effective in generating human-consistent empathetic intents

Abstract

In empathetic conversations, humans express their empathy to others with empathetic intents. However, most existing empathetic conversational methods suffer from a lack of empathetic intents, which leads to monotonous empathy. To address the bias of the empathetic intents distribution between empathetic dialogue models and humans, we propose a novel model to generate empathetic responses with human-consistent empathetic intents, EmpHi for short. Precisely, EmpHi learns the distribution of potential empathetic intents with a discrete latent variable, then combines both implicit and explicit intent representation to generate responses with various empathetic intents. Experiments show that EmpHi outperforms state-of-the-art models in terms of empathy, relevance, and diversity on both automatic and human evaluation. Moreover, the case studies demonstrate the high interpretability and outstanding performance of our model.