Fwd: Talk Announcment: Aida Nematzadeh (DeepMind) - 8/18 11AM

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view
|

Fwd: Talk Announcment: Aida Nematzadeh (DeepMind) - 8/18 11AM

George Duncan-2


---------- Forwarded message ---------
From: Graham Neubig <[hidden email]>
Date: Mon, Aug 17, 2020 at 11:56 AM
Subject: Re: Talk Announcment: Aida Nematzadeh (DeepMind) - 8/18 11AM
To: <[hidden email]>, <[hidden email]>, <[hidden email]>


Hi LTI Folks (also adding MLD in case there is interest),

This is just a reminder that the papers will be the below talk tomorrow, looking forward to seeing people there!

Graham

On Tue, Jul 28, 2020 at 8:00 AM Graham Neubig <[hidden email]> wrote:
Hello LTI Students, Faculty,

I'm happy to announce that we'll be holding a virtual talk by Aida Nematzadeh (http://www.aidanematzadeh.me/), a senior research scientist at DeepMind. Aida has lots of interesting work on language learning inspired by how children learn from their environments. Please see the following for more details!

-------

Title: Learning language by observing the world and learning about the world from language
Time: 8/18 11:00AM
Link: https://cmu.zoom.us/j/91396794981?pwd=WUlTbE85R3Q3cStsUHp5ZHNZa0J5dz09

Children learn about the visual world from implicit supervision that language provides. Most children learn their language, at least to some extent, by observing the world. Recently released datasets of instructional videos are interesting as they can be considered a rough approximation of a child’s visual and linguistic experience -- in these videos, the narrator performs a high-level task (e.g., cooking pasta) while describing the steps involved in that task (e.g., boiling water). Moreover, these datasets pose challenges similar to those children need to address; for example, identifying relevant activities to the task (e.g., boiling water) and ignoring the rest (e.g., shaking head). I will present two recent projects where we study the interaction of visual and linguistic signals in these videos: (1) We show that using language and the structure of tasks is important in discovering action boundaries. (2) I will discuss how visual signal improves the quality of unsupervised word translation, especially for dissimilar languages, and where we do not have access to large corpora.




--
George Duncan
Emeritus Professor of Statistics, Carnegie Mellon University
georgeduncanart.com
See posts on Facebook, Twitter, and Instagram
Land: (505) 983-6895  
Mobile: (505) 469-4671
 
My art theme: Dynamic exposition of the tension between matrix order and luminous chaos.

"Attempt what is not certain. Certainty may or may not come later. It may then be a valuable delusion."

From "Notes to myself on beginning a painting" by Richard Diebenkorn. 

"It's that knife-edge of uncertainty where we come alive to our truest power." Joanna Macy.



- .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. .
FRIAM Applied Complexity Group listserv
Zoom Fridays 9:30a-12p Mtn GMT-6  bit.ly/virtualfriam
un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
archives: http://friam.471366.n2.nabble.com/
FRIAM-COMIC http://friam-comic.blogspot.com/