UTCS Colloquium- Luke Zettlemoyer/University of Washington: "Learning to Follow Orders: Reinforcement Learning for Mapping Instructions to Actions" ACES 2.302, Friday, September 10, 2010 11:00 a.m.

Contact Name: 
Jenna Whitney
Date: 
Sep 10, 2010 11:00am - 12:00pm

There is a sign-up schedule for this event that can be found at

http://www.cs.utexas.edu/department/webevent/utcs/events/cgi/list_event

s.cgi

Type of Talk: UTCS Colloquium

Speaker/Affiliation: Luke Zet

tlemoyer/ University of Washington

Date/Time: Friday, September 10,

2010, 11:00 a.m.

Location: ACES 2.302

Host: Raymond Mooney

Talk Title: Learning to Follow Orders: Reinforcement Learning for Mapping I

nstructions to Actions

Talk Abstract:
In this talk, I will address

the problem of relating linguistic analysis and control --- specifically,

mapping natural language instructions to executable actions. I will present
a reinforcement learning algorithm for inducing these mappings by interact

ing with virtual computer environments and observing the outcome of the exe

cuted actions. This technique has enabled automation of tasks that until no

w have required human participation --- for example, automatically configu

ring software by consulting how-to guides. I will also describe a recent ex

tension for learning to interpret high-level instructions, ones that posit
goals without explicitly describing the actions required to achieve them.

Our results demonstrate that in both cases, the method can rival supervise

d learning techniques while requiring few or no annotated training examples

.

This is joint work with Branavan, Harr Chen and Regina Barzilay. Th

e talk will focus on work published at ACL 2009, where it received a Best

Paper Award, and ACL 2010.

Speaker Bio:
Luke Zettlemoyer is an Assi

stant Professor at the University of Washington in Seattle. He recent compl

eted a postdoctoral research fellowship at the University of Edinburgh and

, before that, received his Ph.D. from MIT. His research interests are in

the intersections of natural language processing, machine learning and dec

ision making under uncertainty.