DSI Distinguished Lecture by Dan Roth: Learning and Inference for Natural Language Understanding

Monday, April 27, 2014
3:00 – 4:00pm, Reception to follow
Hariri Institute for Computing
111 Cummington Mall, Rm 180

Machine Learning and Inference methods have become ubiquitous and have had a broad impact on a range of scientific advances and technologies and on our ability to make sense of large amounts of data. Research in Natural Language Processing has both benefited from and contributed to advancements in these methods and provides an excellent example for some of the challenges we face moving forward.

In his talk, Dan Roth will describe his research in developing learning and inference methods in the pursuit of natural language understanding. Roth will delve deeper into what he believes are key challenges including:

• Learning models from natural interactions without direct supervision
• Knowledge acquisition and the development of inference models capable of incorporating knowledge and reason
• Scalability and adaptation in regards to learning to accelerate inference during the lifetime of a learning system

Within the unified computational framework of Constrained Conditional Models (CCMs) – an Integer Linear Programming formulation that augments statistically learned models with declarative constraints as a way to support learning and reasoning – Roth will discuss old and new results pertaining to learning and inference and how they are used to push forward our ability to understand natural language.

About the speaker:

Dan Roth is a Professor in the Department of Computer Science and the Beckman Institute at the University of Illinois at Urbana/Champaign and a University of Illinois scholar. Roth has published broadly in machine learning, natural language processing, language theory, and knowledge representation and reasoning. He has also developed advanced machine learning based tools for natural language applications that are being used widely by the research community and commercially. Roth is the Associate Editor-in-Chief of the Journal of Artificial Intelligence Research (JAIR) and will serve as Editor-in-Chief for a two-year term beginning in 2015. He was the program chair of AAAI’11, ACL’03 and CoNLL’02. Roth received his BA summa cum laude in Mathematics from Technion in Israel and his PhD in Computer Science from Harvard University in 1995.

About the DSI Distinguished Lecture Series:  
Launched as part of the Data Science Initiative at the Hariri Institute for Computing, the Distinguished Lecture Series brings prominent scholars to Boston University to share their experiences and perspectives on data science as it is manifested through or enabled by their research. Lectures in this series should be of interest to a broad audience as they are meant to promote the exciting advances in the methodologies that enable big-data-driven research in a multitude of disciplines.