Emotion Conditioned Creative Dialog Generation
This work addresses the need for emotion-aware dialog systems, but it is incremental as it builds on existing DialGPT models.
The authors tackled the problem of generating creative dialog responses conditioned on specific emotions, achieving an emotion expression accuracy of 0.6, with neutral, fear, and disgust performing best.
We present a DialGPT based model for generating creative dialog responses that are conditioned based on one of the following emotions: anger, disgust, fear, happiness, pain, sadness and surprise. Our model is capable of producing a contextually apt response given an input sentence and a desired emotion label. Our model is capable of expressing the desired emotion with an accuracy of 0.6. The best performing emotions are neutral, fear and disgust. When measuring the strength of the expressed emotion, we find that anger, fear and disgust are expressed in the most strong fashion by the model.