Dr. Peter Wiemer-Hastings
DePaul University
http://reed.cs.depaul.edu/peterwh/

Wednesday, September 22 
4:00 pm - 5:30 pm (LSci 175)

Title 
=====

From Tutoring to Turing: Latent Semantic Analysis as Cognitive Model
and Budget Natural Language Understanding

Abstract
========

This talk will center on Latent Semantic Analysis (LSA), a vector-based  
technique for representing and comparing texts. Following a brief history  
of LSA and description of the process by which its representations are  
built, LSA will be discussed as a model for human language learning and  
representation.  Despite the fact that it ignores syntax altogether, LSA  
has neared or matched human performance on a variety of tasks.  For  
single-sentence texts, however, LSA does not perform well, presumably due  
(at least in part) to its ignorance of syntax.  Recent research has  
explored methods for augmenting LSA with various types of structural  
knowledge.  This work parallels psychological studies on the effects of  
structure on similarity judgments.  The talk will conclude with  
descriptions of applications of LSA as an expectation-based natural  
language understanding mechanism.

Biographical Information
========================

Peter Wiemer-Hastings is an Assistant Professor in the School of Computer    
Science, Telecommunications, and Information Systems at DePaul University.   
Before coming to DePaul he was at the University of Edinburgh where he    
was a Lecturer. Prior to his move to Scotland, he worked as a   
post-doctoral research assistant at the University of Memphis. Before  
that, he was awarded a postdoctoral fellowship at the University of  
Michigan in Ann Arbor, where he earned his Ph.D. in computer science. He  
completed his masters degree at the Johns Hopkins University and his  
undergraduate degree at Michigan State University, both in computer  
science. Dr. Wiemer-Hastings's research interests include natural language  
processing, cognitive science, intelligent tutoring systems, and  
artificial intelligence.