NLP Seminar: Jiwei Li (Stanford University), "Teaching Machines to Converse"

Date: 
Wednesday, April 26, 2017 - 2:00pm to 3:00pm
Location: 
1132 Harold Frank Hall
Title: 
Teaching Machines to Converse
Speaker: 
Jiwei Li (Stanford University)
Host: 
William Wang

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) using adversarial learning for dialogue generation. 

Bio

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 (william@cs.ucsb.edu). 

Everyone welcome!