AI Forum: Deb Roy/Massachusetts Institute of Technology Meaning Machines in ACES 2.302

Contact Name: 
Jenna Whitney
Date: 
Aug 31, 2006 3:30pm - 4:30pm


There is a signup schedule for this event.

Speaker Name/Af

filiation: Deb Roy/Massachusetts Institute of Technology

Date/Time:

Friday September 1 2006 at 3:00 p.m.

Location: ACES 2.302

H

ost: Benjamin Kuipers

Talk Title: Meaning Machines

Talk A

bstract:
People use words to refer to the world as a means for
influe

ncing the beliefs and actions of others. Although many
isolated aspects

of the structure and use of language have been
extensively studied a un

ified model of situated language use
remains unexplored. Any attempt to

explain unconstrained adult
language use appears futile due to the overw

helming complexity
of the physical cognitive and cultural factors at p

lay. A
strategy for making progress towards a holistic account of
lan

guage use is to study simple forms of language (e.g.
conversational spe

ech about objects and events in the
here-and-now in limited social conte

xts) and strive for
vertically integrated computational models. I will p

resent
experiments guided by this strategy in building conversational
robots and natural language interfaces for video games. An
emerging fra

mework suggests a semiotic perspective may be
useful for designing syste

ms that process language grounded in
social and physical context.

Speaker Bio:
Deb Roy is Associate Professor of Media Arts and Scie

nces at
the Massachusetts Institute of Technology. He is Director of

the Cognitive Machines Group at the MIT Media Laboratory which
he founde

d in 2000. Roy also directs the 10x research program
a lab-wide effort
to design new technologies for enhancing
human cognitive and physical c

apabilities. Roy has published
numerous peer-reviewed papers in the area

s of knowledge
representation speech and language processing machineperception robotics information retrieval cognitive
modeling and h

uman-machine interaction and has served as
guest editor of the journal

Artificial Intelligence. He has
lectured widely in academia and industry

. His work has been
featured in various popular press venues including t

he New York
Times the Globe and Mail CNN BBC and PBS. In 2003 Roy wa

s
appointed AT&T Career Development Professor. He holds a B.A.Sc.
in

Computer Engineering from University of Waterloo and a
Ph.D. in Media A

rts and Sciences from MIT.