'''
报告人：Kewei Tu时间：2015 年 5 月 27 日（星期三）下午 2:00地点：张江校区软件楼 102 第二会议室联系人：肖仰华 (shawyh@fudan.edu.cn)Abstract:Stochastic grammars are a probabilistic extension of formal grammars, which are widely used in the domain of natural language processing. In this talk, I will show how stochastic grammars can be extended to model other types of data such as hierarchical spatial compositions of objects and scenes, hierarchical temporal compositions of events, and probability distributions of vector data. A main obstacle to the application of stochastic grammars is that good grammars are very difficult to construct. Therefore, I will further discuss a few unsupervised approaches to learning stochastic grammars.Bio:Dr. Kewei Tu is an Assistant Professor with the School of Information Science and Technology at ShanghaiTech University, Shanghai, China. He received BS and MS degrees in Computer Science and Technology from Shanghai Jiaotong University, China in 2002 and 2005 respectively and received a PhD degree in Computer Science from Iowa State University, USA in 2012. During 2012-2014, he worked as a postdoctoral researcher at the Vision, Cognition, Learning and Art Laboratory, Departments of Statistics and Computer Science of the University of California, Los Angeles, USA. His research interests include stochastic grammars, machine learning, knowledge representation, natural language processing, and computer vision.
'''
