MoEL: Mixture of Empathetic Listeners
arXiv:1908.07687
Abstract
Previous research on empathetic dialogue systems has mostly focused on generating responses given certain emotions. However, being empathetic not only requires the ability of generating emotional responses, but more importantly, requires the understanding of user emotions and replying appropriately. In this paper, we propose a novel end-to-end approach for modeling empathy in dialogue systems: Mixture of Empathetic Listeners (MoEL). Our model first captures the user emotions and outputs an emotion distribution. Based on this, MoEL will softly combine the output states of the appropriate Listener(s), which are each optimized to react to certain emotions, and generate an empathetic response. Human evaluations on empathetic-dialogues (Rashkin et al., 2018) dataset confirm that MoEL outperforms multitask training baseline in terms of empathy, relevance, and fluency. Furthermore, the case study on generated responses of different Listeners shows high interpretability of our model.
arXiv commentAccepted by EMNLP2019
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- A Neural Conversational Model
- Wizard of Wikipedia: Knowledge-Powered Conversational agents
- How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
- Deep Reinforcement Learning for Dialogue Generation
- TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
- One Model To Learn Them All
- Nonlinear Models Using Dirichlet Process Mixtures
- Generative Image Modeling Using Spatial LSTMs
- Generative Deep Neural Networks for Dialogue: A Short Review
- Personalization in Goal-Oriented Dialog
- Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
- Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory