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.
@article{arxiv.1907.12108,
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 preprint arXiv:1907.12108},
year = {2020}
}