[Colloquium] Computational Intelligence Talks: a joint venture between the Computation Institute and Knowledge Lab

[Ninfa Mayorga]

Computational Intelligence Talks: a joint venture between the Computation Institute and Knowledge Lab

Speaker:  David McAllester, Chief Academic Officer, Toyota Technological Institute at Chicago
Host:  James A. Evans
Date:  October 27, 2014
Time:  3:00 PM - 4:15 PM
Location:  University of Chicago, Searle 240A, 5735 S. Ellis Ave.   

The Problem of Reference
 
Abstract: This talk will present an approach to the semantics of natural language focusing on the problem of reference.  Phrases of natural language refer to things in the world such as "Obama", "Air Force One", "the Malaysian airliner that disappeared" or "the occupation of Crimea".  Sampled sentences will be used to argue that resolving references is essential to any treatment of semantics.  The discussion of natural language semantics will include both philosophical considerations, such as the notion of "a thing in the world" and the problem of grounding, as well as concrete engineering problems such as achieving good performance on the NAACL coreference evaluation.  A new grammar formalism for modeling reference --- entity grammars --- will also be presented.
 
Bio: Professor McAllester received his B.S., M.S., and Ph.D. degrees from the Massachusetts Institute of Technology in 1978, 1979, and 1987 respectively. He served on the faculty of Cornell University for the academic year of 1987-1988 and served on the faculty of MIT from 1988 to 1995. He was a member of technical staff at AT&T Labs-Research from 1995 to 2002. He has been a fellow of the American Association of Artificial Intelligence (AAAI) since 1997. Since 2002 he has been Chief Academic Officer at the Toyota Technological Institute at Chicago (TTIC). He has authored over 100 refereed publications.

Professor McAllester's research areas include machine learning, the theory of programming languages, automated reasoning, AI planning, computer game playing (computer chess), computational linguistics and computer vision. A 1991 paper on AI planning proved to be one of the most influential papers of the decade in that area. A 1993 paper on computer game algorithms influenced the design of the algorithms used in the Deep Blue system that defeated Gary Kasparov. A 1998 paper on machine learning theory introduced PAC-Bayesian theorems which combine Bayesian and nonBayesian methods. A 2001 paper with Andrew Appel introduced the influential step indexed model of recursive types in programming languages. He was part of a team (with Pedro Felzenszwalb, Ross Girshick and Deva Ramanan) that developed the first high-performance system based on a deformable part model for object detection in computer vision. This team scored in the top two places in the PASCAL object detection challenge (computer vision) in 2007, 2008 and 2009. He is currently working on algorithms for holistic scene understanding and on a type-theoretic foundation for mathematics.

Information:  Refreshments will be provided


-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20141023/3bbd8aba/attachment.htm