Snowbot: An empirical study of building chatbot using seq2seq model with different machine learning framework

Chatbot is a growing topic, we built a open domain generative chatbot using seq2seq model with different machine learning framework (Tensorflow, MXNet). Our result show although seq2seq is a successful method in neural machine translation, use it solely on single turn chatbot yield pretty unsatisfactory result. Also existing free dialog corpus lacks both quality and quantity. Our conclusion it’s hard to build a useful open domain generative bot using state of art technology.