— Human-Computer Conversation —
DR-D3Q: Dynamic Reward-based Dueling Deep Dyna-Q (2019)
Cross-Domain Sentiment Transfer (2019)
EsCVAE: Learning to Converse Emotionally Like Humans (2018)
Emotional intelligence is one of the key parts of human intelligence. Exploring how to endow conversation models with emotional intelligence is a recent research hotspot. Although several emotional conversation approaches have been introduced, none of these methods were able to decide an appropriate emotion category for the response. In this paper, we propose the EsCVAE-I and EsCVAE-II model to learn to automatically specify a reasonable emotion category for response generation. We show that there are some frequent emotion interaction patterns in humans dialogue (e.g. happiness-like, angry-disgust), and our models are able to learn such frequent patterns and apply it to emotional conversation generation. Experiments show that our proposed approaches can generate appropriate emotion and yield significant improvements over the baseline methods in emotional conversation.