Please join us for the NLP Seminar this Monday, Oct 31 at 3:30pm in 202 South Hall. All are welcome!
Speaker: Jiwei Li (Stanford)
Title: Teaching Machines to Converse
Abstract:
Recent neural networks models present both new opportunities and new challenges for developing conversational agents. In this talk, I will describe how we have advanced this line of research by addressing four different issues in neural dialogue generation: (1) overcoming the overwhelming prevalence of dull responses (e.g., “I don’t know”) generated from neural models; (2) enforcing speaker consistency; (3) applying reinforcement learning to foster sustained dialogue interactions. (4) How to teach a bot to interact with users and ask questions about things that he does not know.
(Slides)