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) using adversarial learning for dialogue generation.
Jiwei Li is a third-year Ph.D. student in the Computer Science Department at Stanford University, advised by Professor Dan Jurafsky. His research interests lie in Natural Language Processing, with a focus on deep learning applications in language generation, dialogues, and discourses.
NOTE: If you would like to meet with the speaker, please contact the host (firstname.lastname@example.org).