Chatbots is hot (and hard). In this talk, I will summarize our recent efforts in leveraging deep learning techniques to facilitate easy data access and build user friendly chatbots. The evolution and the connection among information retrieval, natural language interfaces to databases, task oriented and open domain conversational agents will be introduced. I will then discuss key issues in advancing conversational techniques including state awareness, knowledge grounding and fact checking. Solving these issues could lead us to general conversational agents in the future.
Xifeng Yan is a professor at the University of California at Santa Barbara, holding the Venkatesh Narayanamurti Chair of Computer Science. He received his Ph.D. degree in Computer Science from the University of Illinois at Urbana-Champaign in 2006 and was a research staff member at the IBM T. J. Watson Research Center between 2006 and 2008. His research contribution can be found in data mining, database systems, natural language processing, etc. Recently he is working on knowledge graph, natural language interfaces to data and dialogue systems. His works were extensively referenced, with over 21,000 citations per Google Scholar and thousands of software downloads. He received NSF CAREER Award, IBM Invention Achievement Award, ACM-SIGMOD Dissertation Runner-Up Award, and IEEE ICDM 10-year Highest Impact Paper Award.