A Neural Network based Vietnamese Chatbot

Nowadays, chatbot is a hot topic, chatbots are built from generative models are gaining success. The purpose of this article is to build a Vietnamese chatbot based on the seq2seq model incorporating the attention mechanism. We have built the model and tested on deep learning framework Pytorch using GPU. The model was trained end-to-end with no hand-crafted rules. Model is built from a small dataset and can generate responses to a user. However, generated responses still need to be improved to get a meaningful conversation.