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.
Recommended citation: Lin, Z., Xu, P., Winata, G. I., Liu, Z., & Fung, P. (2019). CAiRE: An End-to-End Empathetic Chatbot. arXiv preprint arXiv:1907.12108.