CAiRE: An Empathetic Neural Chatbot

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.

arXiv commentExtended version of AAAI-2020 demo paper

References in corpus (2)

• Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books
• TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents

Cited by in corpus (8)

• Empathetic Conversational Systems: A Review of Current Advances, Gaps, and Opportunities
• Attention over Parameters for Dialogue Systems
• Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning
• Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution
• Open-Domain Dialogue Generation Based on Pre-trained Language Models
• EmpBot: A T5-based Empathetic Chatbot focusing on Sentiments
• A Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue Generation
• Coral: An Approach for Conversational Agents in Mental Health Applications