Emotion Conditioned Creative Dialog Generation

TL;DR

This paper introduces a DialGPT-based model that generates emotionally conditioned creative dialogue responses, achieving notable accuracy in expressing specific emotions like fear and disgust within conversational contexts.

Contribution

The work presents a novel emotion-conditioned dialogue generation model capable of producing contextually relevant responses with specific emotional expressions.

Findings

Emotion expression accuracy of 0.6

Neutral, fear, and disgust are most accurately expressed

Anger, fear, and disgust are expressed most strongly

Abstract

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.