Towards An Open-Domain Dialog System

Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. In this talk, we use Microsoft XiaoIce [1] as a case study to discuss the state-of-the-art conversational AI [2], focusing on three types of dialogues: (1) question answering bots that can provide concise direct answers to user queries; (2) task-oriented bots that can help users accomplish tasks ranging from meeting scheduling to vacation planning; and (3) social bots which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender.