Corpus ID: 216552995

CAiRE: An Empathetic Neural Chatbot.

  title={CAiRE: An Empathetic Neural Chatbot.},
  author={Zhaojiang Lin and Peng Xu and Genta Indra Winata and Farhad Bin Siddique and Zihan Liu and Jamin Shin and Pascale Fung},
  journal={arXiv: Computation and Language},
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… Expand
7 Citations

Figures and Tables from this paper

A Modular Data-Driven Architecture for Empathetic Conversational Agents
Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intention
  • PDF
Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution
  • 9
  • PDF
Generalized Conditioned Dialogue Generation Based on Pre-trained Language Model
  • 1
  • PDF
Open-Domain Dialogue Generation Based on Pre-trained Language Models
  • PDF
Towards Persona-Based Empathetic Conversational Models
  • 3
  • PDF


MoEL: Mixture of Empathetic Listeners
  • 26
  • PDF
Personalizing Dialogue Agents via Meta-Learning
  • 58
  • PDF
Deep contextualized word representations
  • 5,437
  • PDF
Attention is All you Need
  • 16,989
  • PDF