The proliferation of the Internet has led to an unprecedented amount of textual information, far exceeding humans’ ability to read and understand text. This calls for automatic text processing techniques to unlock different kinds of information embedded in text. Over the past few decades, much progress has been made in the extraction of named entities (e.g., person, organization) and binary relations between entities. However, progress in the extraction of more complex information, such as opinions and events, has been slow. In this talk, I will describe new techniques for extracting opinions and events and representing such information in structured forms, readable by machines and interpretable by humans.
Bio: Bishan Yang is a Postdoctoral Fellow in the Machine Learning Department at Carnegie Mellon University. She completed her Ph.D. in Computer Science at Cornell University and received her B.S. and M.S. in Computer Science from Peking University. She received the Olin Fellowship for her first-year study at Cornell. Her research interest is in developing machine learning and natural language processing techniques to people use and manage large-scale textual information more efficiently and effectively.