With the recent remarkable growth of speech-enabled applications, statistical dialog modeling has become a critical component not only for typical telephone-based spo-ken dialog systems but also for multi-modal dialog systems on mobile devices and in automobiles. Due to present Automatic Speech Recognition and Spoken Language Understanding uncertainty, it is crucial to accurately track dialog states by updating the probability distribution over possible dialog states as a dialog unfolds. I will intro-duce some of the recent advances to make dialog state tracking to be more robust to common errors generated by live users that have been shown to be very effective by largely outperforming previous state-of-the-art systems in the Dialog State Tracking Challenge. Given the significant size of dialog state space, it is almost impossible to design effective dialog strategies by hand. It is therefore desirable to have a machine automatically optimize the dialog strategies. Most policy learning algorithms, however, require a significant number of training dialogs, which can prove to be costly and time-consuming for real users. Thus I present two different ways to address this problem. First I will describe a rapid reinforcement learning method based on sparse Bayesian regression which removes the preprocessing steps for hyper-parameter learn-ing, thus achieving fully online policy learning. Second I describe an unsupervised method to automatically build a simulated user from system's log files, which can be crucial for a deployed system furnishing a stream of live data.
Dr. Sungjin Lee is a Post-doctoral research fellow in Language Technologies Institute at Carnegie Mellon University. He received his PhD from the Pohang University of Science and Technology in 2012. His research interests lie in various areas of speech and language processing as well as machine learning. He is primarily working on statistical dialog modeling which includes structured discriminative models for dialog state tracking, sparse Bayesian models for online dialog strategy learning and unsupervised methods for user simulation. He is also interested in applying spoken language technologies to computer-assisted language learning settings. He serves on the advisory boards of Dialog State Tracking Challenge and Real Challenge. He is a member of Program Committee of many prestigious conferences.
Faculty Host: Maxine Eskenazi