From - Fri Feb 13 08:37:48 2004
X-Mozilla-Status: 0001
X-Mozilla-Status2: 00000000
Path: acsu.buffalo.edu!rapaport
From: rapaport@cse.buffalo.edu (William J. Rapaport)
Newsgroups: sunyab.cse.740
Subject: CogSci: Hastings on Latent Semantic Analysis
Date: Thu, 12 Feb 2004 13:30:22 -0500 (EST)
Organization: Computer Science and Engineering
Lines: 65
Sender: Ncs@buffalo.edu
Distribution: sunyab
Message-ID: <c0ggnu$p46$1@prometheus.acsu.buffalo.edu>
NNTP-Posting-Host: wasat.cse.buffalo.edu
X-Trace: prometheus.acsu.buffalo.edu 1076610622 25734 128.205.32.15 (12 Feb 2004 18:30:22 GMT)
X-Complaints-To: abuse@buffalo.edu
NNTP-Posting-Date: Thu, 12 Feb 2004 18:30:22 +0000 (UTC)
X-Newsreader: trn 4.0-test76 (Apr 2, 2001)
Xref: acsu.buffalo.edu sunyab.cse.740:73


                     CENTER FOR COGNITIVE SCIENCE
         University at Buffalo, State University of New York

                     Wednesday, February 18, 2004
                          2:00 pm - 4:00 pm
                     280 Park Hall, North Campus


                     Peter Wiemer-Hastings, Ph.D.
            School of Computer Science, Telecommunication,
              and Information Systems, DePaul University


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


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. Research by Dennis
et al, Kanejiya et al, and myself has explored 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.






A hardcopy of this announcement can be accessed here:
http://www.cogsci.buffalo.edu/Activities/Colloquium/CLLQs04/hastingsannouncement.pdf

Please print it out and post it in your department. Thank you!


                     Center for Cognitive Science
         University at Buffalo, State University of New York
                  652 Baldy Hall, Buffalo, NY 14260
              Phone: (716) 645-3794, Fax: (716) 645-3825
                Email: ccs-cogsci-contact@buffalo.edu
http://www.cogsci.buffalo.edu/Activities/Colloquium/CLLQs04/2004spring.htm


     All Center for Cognitive Science Events are sponsored by the
              Office of the Vice President for Research
                        University at Buffalo
                     State University of New York

Center for Cognitive Science
University at Buffalo
652 Baldy Hall
Buffalo, NY 14260
P: (716) 645-2177 ext. 717
F: (716) 645-3825
Email: ccs-cogsci-contact@buffalo.edu
URL: http://www.cogsci.buffalo.edu

