MOOC Guider: An End-to-End Dialogue System for MOOC Users

With the growth of the amount of MOOC users and course diversity, it becomes a hard work for a new MOOC user to find a suitable course and gather other information. In this paper, we propose a natural language dialogue based MOOC guider, which helps users to find a preferred course and provide more information of courses according to a user’s requests. Our method is an end-to-end neural network based method and can be trained efficiently using multi-stage training. Experiments show that our method can understand users’ intent well and produce proper response to finish the task.