GANChat : A Generative Adversarial Network approach for chat bot learning

Abstract: Recently a new method for training generative neural networks called Generative Adversarial Networks (GAN) has shown great results in the computer vision domain and shown potential in other generative machine learning tasks as well. GAN training is an adversarial training method where two neural networks compete and attempt to outperform each other, and in the process they both learn. In this thesis the effectiveness of GAN training is tested on conversational agents also called chat bots. To test this, current state-of-the-art training methods such as Maximum Likelihood Estimation (MLE) models are compared with GAN method trained models. Model performance was measured by closeness of the model distribution from the target distribution after training. This thesis shows that the GAN method performs worse the MLE in some scenarios but can outperform MLE in some cases.