[Theory] CANCELED! : 3/16 TTIC Colloquium: Raymond Mooney, University of Texas at Austin

Mary Marre mmarre at ttic.edu
Thu Mar 12 13:22:18 CDT 2020


 *The 3/16 Colloquium talk is **CANCELED!*


*( Reschedule date will be announced when confirmed)*



*#######################################################################*


*When:*      Monday, March 16th at 11:00 am



*Where:*     TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526



*Who: *       Raymond Mooney, University of Texas at Austin




*Title:*       A Review of Work on Natural Language Navigation Instructions


*Abstract:* Over the past decade or so, there has been a series of
increasingly challenging projects on comprehending and generating
navigation instructions in natural language.  Using a dataset initially
assembled by MacMahon et al. in 2006, we (Chen & Mooney, 2011) were the
first to try to learn to understand navigation instructions by observing
human instructors and followers in a simple simulated maze environment.
Subsequently, there was a sequence of projects, most recently using deep
learning, that steadily improved the ability to both comprehend and
generate navigation instructions using this data. More recently, the Vision
Language Navigation (VLN) challenge was introduced that requires following
instructions in very detailed 3D graphics simulations of realistic houses,
as well as the Touchdown challenge that requires following outdoor
navigation instructions using Google Street View. Finally, I will review
our recent work on developing  a system that uses multiple mobile robots to
provide navigation guidance to newcomers to our office building by
optimally combining robots explicitly leading patrons and giving them
natural-language instructions.


*Bio: *Raymond J. Mooney is a Professor in the Department of Computer
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 author of
over 170 published research papers, primarily in the areas of machine
learning and natural language processing. He was the President of the
International Machine Learning Society from 2008-2011, program co-chair for
AAAI 2006, general chair for HLT-EMNLP 2005, and co-chair for ICML 1990. He
is a Fellow of AAAI, ACM, and ACL and the recipient of the Classic Paper
award from AAAI-19 and best paper awards from AAAI-96, KDD-04, ICML-05 and
ACL-07.



*Host:* David McAllester <mcallester at ttic.edu>


For more information on the colloquium series or to subscribe to the
mailing list, please see http://www.ttic.edu/colloquium.php



Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 517*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*


On Mon, Mar 9, 2020 at 3:53 PM Mary Marre <mmarre at ttic.edu> wrote:

> *When:*      Monday, March 16th at 11:00 am
>
>
>
> *Where:*     TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526
>
>
>
> *Who: *       Raymond Mooney, University of Texas at Austin
>
>
>
>
> *Title:*       A Review of Work on Natural Language Navigation
> Instructions
>
>
> *Abstract:* Over the past decade or so, there has been a series of
> increasingly challenging projects on comprehending and generating
> navigation instructions in natural language.  Using a dataset initially
> assembled by MacMahon et al. in 2006, we (Chen & Mooney, 2011) were the
> first to try to learn to understand navigation instructions by observing
> human instructors and followers in a simple simulated maze environment.
> Subsequently, there was a sequence of projects, most recently using deep
> learning, that steadily improved the ability to both comprehend and
> generate navigation instructions using this data. More recently, the Vision
> Language Navigation (VLN) challenge was introduced that requires following
> instructions in very detailed 3D graphics simulations of realistic houses,
> as well as the Touchdown challenge that requires following outdoor
> navigation instructions using Google Street View. Finally, I will review
> our recent work on developing  a system that uses multiple mobile robots to
> provide navigation guidance to newcomers to our office building by
> optimally combining robots explicitly leading patrons and giving them
> natural-language instructions.
>
>
> *Bio: *Raymond J. Mooney is a Professor in the Department of Computer
> 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 author of
> over 170 published research papers, primarily in the areas of machine
> learning and natural language processing. He was the President of the
> International Machine Learning Society from 2008-2011, program co-chair for
> AAAI 2006, general chair for HLT-EMNLP 2005, and co-chair for ICML 1990. He
> is a Fellow of AAAI, ACM, and ACL and the recipient of the Classic Paper
> award from AAAI-19 and best paper awards from AAAI-96, KDD-04, ICML-05 and
> ACL-07.
>
>
>
> *Host:* David McAllester <mcallester at ttic.edu>
>
>
> For more information on the colloquium series or to subscribe to the
> mailing list, please see http://www.ttic.edu/colloquium.php
>
>
>
> Mary C. Marre
> Faculty Administrative Support
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 517*
> *Chicago, IL  60637*
> *p:(773) 834-1757*
> *f: (773) 357-6970*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20200312/945a5585/attachment-0001.html>


More information about the Theory mailing list