Guest Speaker: Jiwei Li
Third-year Ph. D. Student at Stanford University
September 26, 2016, 4:00 pm, 480 Dreese Labs
Teaching a Machine to Converse
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.
Bio: Jiwei Li is a third-year PH.D. student in the computer science department at Stanford University. He is advised by Prof. Dan Jurafsky, and also works closely with Facebook AI Research and the NLP group at MSR. He works on natural language processing, with a focus on deep learning. Jiwei receives his B.S. from Peking University in 2012. He was rewarded the Facebook Fellowship in 2015.
Host: Alan Ritter