The 2011 Visions of Computing Lecture Series - Raymond Mooney, William Press and Tandy Warnow, ACES 2.302

Contact Name: 
Jenna Whitney
Oct 26, 2011 4:00pm - 5:30pm

The 2011 Visions of Computing Lecture Series

Speakers: Ray

mond Mooney, William Press, and Tandy Warnow/The University of Texas at A

ustin Department of Computer Science

Wednesday, October 26, 2011

CES 2.302 – AVAYA Auditorium 4:00 p.m. - 5:30 pm

Host: The Departme

nt of Computer Science

A live webcast will be available at: http://med


Talk Titles/Abstracts/Speaker Bios:

4:00 – 4:30 pm

1) Raymond Mooney - "Learning Natural Language from its Perceptual Context"

Awarded Fellow of the Association for Computing Machinery


learning has become the best approach to building systems that comprehend h

uman language. However, current systems require a great deal of laboriousl

y constructed human-annotated training data. Ideally, a computer would be

able to acquire language like a child by being exposed to linguistic input

in the context of a relevant but ambiguous perceptual environment. As a ste

p in this direction, we have developed systems that learn to sportscast si

mulated robot soccer games and to follow navigation instructions in virtual
environments by simply observing sample human linguistic behavior. This wo

rk builds on our earlier work on supervised learning of semantic parsers th

at map natural language into a formal meaning representation. In order to a

pply such methods to learning from observation, we have developed methods

that estimate the meaning of sentences from just their ambiguous perceptual

Bio: Raymond J. Mooney is a Professor in the Department of C

omputer Science at the University of Texas at Austin. He received his Ph.D.
in 1988 from the University of Illinois at Urbana/Champaign. He is an auth

or of over 150 published research papers, primarily in the areas of machin

e learning and natural language processing. He was the President of the Int

ernational Machine Learning Society from 2008-2011, was program co-chair f

or the 2006 AAAI Conference on Artificial Intelligence, general chair of t

he 2005 Human Language Technology Conference and Conference on Empirical Me

thods in Natural Language Processing, and co-chair of the 1990 Internation

al Conference on Machine Learning. He is a Fellow of both the American Asso

ciation for Artificial Intelligence and the Association for Computing Machi

nery, and the recipient of best paper awards from the National Conference

on Artificial Intelligence, the SIGKDD International Conference on Knowled

ge Discovery and Data Mining, the International Conference on Machine Lear

ning, and the Annual Meeting of the Association for Computational Linguist

ics. His recent research has focused on learning for natural-language proce

ssing, connecting language and perception, statistical relational learnin

g, and transfer learning.

4:30 – 5:00 pm
2) William Press - "Visi

ons of a National Learning Health Care System"
Named Vice Chair of PCAST

and President Elect of AAAS

As health information becomes increasingly
electronic, many improvements in health care delivery, and in the scienc

e underlying medical advances, become possible. This talk will review some
of these and highlight where they suggest important research agendas in co

mputer science.

Bio: William H. Press is the Warren J. and Viola M. Ra

ymer Professor in Computer Science and Integrative Biology at the Universit

y of Texas at Austin. Previously, he was Deputy Director of Los Alamos Nat

ional Laboratory. Much of his earlier career was at Harvard University, wh

ere he was a professor of physics and astronomy. Press is a current member

of President Obama''s Council of Advisors on Science and Technology. He is

also President-elect of the American Association for the Advancement of Sci


5:00 – 5:30 pm
3) Tandy Warnow - "Recent breakthroughs in ma

thematical and computational phylogenetics"
Awarded Guggenheim Fellowship

Phylogenetic trees represent the evolutionary history of a set of spe

cies (or genes), and are important for much biological research. Almost al

l of the methods used to construct phylogenetic trees are computationally v

ery intensive (typically being based upon attempts to solve NP-hard optimiz

ation problems), most make unrealistic assumptions about the evolutionary

process, and few have been tested under realistic conditions. In this talk
I will describe recent breakthroughs in phylogenetic analysis, including

mathematical results regarding estimation under stochastic models of evolut

ion, and novel algorithmic approaches that provide higher accuracy on biol

ogical and simulated datasets.

Bio: Tandy Warnow is the David Bruton J

r. Centennial Professor in Computer Sciences at UT-Austin. Her research com

bines mathematics, computer science, and statistics to develop improved m

odels and algorithms for reconstructing complex and large-scale evolutionar

y histories in both biology and historical linguistics. She received the Na

tional Science Foundation Young Investigator Award in 1994, the David and

Lucile Packard Foundation Award in Science and Engineering in 1996, a Radc

liffe Institute Fellowship in 2006. She currently holds a Guggenheim Founda

tion Fellowship.

Warnow received her PhD in Mathematics at UC Berkeley
under the direction of Gene Lawler. From 1991-1992 she was a postdoctoral

fellow with Simon Tavaré and Michael Waterman at USC, and from 1992-1993

a member of the Discrete Algorithms group at Sandia National Laboratories.

She spent 1993-1999 at the University of Pennsylvania, where she received

tenure. In 1999, she joined the CS faculty at UT-Austin as an Associate Pr

ofessor, and was promoted to Full Professor in 2003. She is a member of fi

ve graduate programs at the University of Texas, including Computer Scienc

e Ecology, Evolution, and Behavior Molecular and Cellular Biology Mathema

tics and Computational and Applied Mathematics. Her national service includ

es membership on several advisory committees for the NAS, NRC, IOM, and

Howard Hughes. She was a member of the Board of Directors for the Internati

onal Society for Computational Biology, and is the Chair of the BDMA (Biod

ata Management and Analysis) study section at NIH.