- This event has passed.
2020 Heilmeier Award Lecture, Dr. Dan Roth
January 19, 2021 at 3:00 PM - 4:00 PM
“It’s Time for Reasoning”
This event will take place via Zoom Webinar, click here to join.
Password: 374986
The lecture will be recorded and will be made available for viewing here.
Dan Roth
Eduardo D. Glandt President’s Distinguished Professor in Computer and Information Science
Biography
Dan Roth is the Eduardo D. Glandt President’s Distinguished Professor of Computer and Information Science in the School of Engineering and Applied Science at the University of Pennsylvania.
Dr. Roth’s research interests are in the computational foundations of intelligent behavior. He develops theories and systems pertaining to intelligent behavior using a unified methodology – at the heart of which is the idea that learning has a central role in intelligence. His research has contributed to major conceptual and theoretical advances in the modeling of natural language understanding, machine learning, and reasoning. In recent years he has focused on the study of machine learning and inference methods to facilitate natural language understanding and has also developed advanced machine learning based tools for natural language applications that are being used widely by the research community and commercially.
Abstract
The fundamental issue underlying natural language understanding is that of semantics – there is a need to move toward understanding natural language at an appropriate level of abstraction in order to support natural language understanding and communication with computers.
Machine Learning has become ubiquitous in our attempt to induce semantic representations of natural language and support decisions that depend on it; however, while we have made significant progress over the last few years, it has focused on classification tasks for which we have large amounts of annotated data. Supporting high level decisions that depend on natural language understanding is still beyond our capabilities, partly since most of these tasks are very sparse and generating supervision signals for it does not scale.
I will discuss some of the challenges underlying reasoning – making natural language understanding decisions that depend on multiple, interdependent, models, and exemplify it using the domain of Reasoning about Time, as it is expressed in natural language.