CAiRE: An Empathetic Neural Chatbot
This work addresses the need for more emotionally aware conversational AI, though it is incremental as it builds on existing methods like TransferTransfo.
The paper tackles the problem of creating an empathetic chatbot by fine-tuning a pre-trained language model with multi-task objectives, achieving state-of-the-art performance on dialogue emotion detection and empathetic response generation on the empathetic-dialogues dataset.
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.