CAiRE: An Empathetic Neural Chatbot

TL;DR

This paper introduces CAiRE, an empathetic chatbot that fine-tunes a large-scale pre-trained language model with multi-task learning to generate emotionally aware responses, achieving state-of-the-art results.

Contribution

It presents a novel end-to-end empathetic conversation system that combines transfer learning with multi-task objectives for improved emotional response generation.

Findings

Achieves state-of-the-art performance in dialogue emotion detection.

Outperforms previous models in empathetic response generation.

Demonstrates effectiveness of multi-task learning in empathetic chatbots.

Abstract

In this paper, we present an end-to-end empathetic conversation agent CAiRE. Our system adapts TransferTransfo (Wolf et al., 2019) learning approach that fine-tunes a large-scale pre-trained language model with multi-task objectives: response language modeling, response prediction and dialogue emotion detection. We evaluate our model on the recently proposed empathetic-dialogues dataset (Rashkin et al., 2019), the experiment results show that CAiRE achieves state-of-the-art performance on dialogue emotion detection and empathetic response generation.