Colloquium Details
A New Approach to implementing Goal-driven Dialogue System
| Author: | Ji Wu, Associate Professor Tsinghua University, China |
|---|---|
| Date: | August 19, 2016 |
| Time: | 15:30 |
| Location: | 220 Deschutes |
Abstract
Dialogue system (Chatbot) is becoming a very hot topic and fascinating technology trend both in acadmic community and industries. Google, Fackbook, Microsoft and many startups seem to believe that Chatbots will be a new generation of apps after websites and mobile apps. Many dialog systems have been implemented to provide a variety of services, such as call routing, flight booking, weather forecasting, and restaurants recommendation. Those goal-driven dialog systems enable a human user to acquire information and services by interacting with a computer agent using natural languages. Although the future is considered to be extremely bright, there are still a lot of difficulties, such as inevitable speech recognition (SR) errors and natural language understanding (NLU) errors, strategies to control the multi-turn dialog process, and etc. In this talk, I will present a probabilistic framework for representing interactive dialog processes. A new target-based state is then defined to characterize the goal set of a dialog state. Furthermore, an entropy minimization dialog management (EMDM) strategy is proposed to combine with the target-based states to facilitate a robust and efficient solution in reaching a user's goals. With the proposed approach, the user and the system can work collaboratively to achieve the users goal in an efficient manner.
Biography
Ji Wu is an Associate Professor in the Department of Electronic Engineering, Tsinghua University, Beijing, China. He received his B.S. and Ph.D degrees from Tsinghua University, in 1996 and 2001, respectively, both in Electronic Engineering. He is leading the Multimedia Signal and Intelligence Information Processing Lab at Tsinghua University. Since 2006, he has been the director of Tsinghua-iFlyTek Joint Lab for Speech Technologies. He is also the leader of SIAC-TWG (Technical Work Group of Speech Industry Alliance of China). His research interests include natural language processingļ¼speech recognition, pattern recognition, machine learning and data mining.