[FRIAM] Fwd: Talk Announcment: Aida Nematzadeh (DeepMind) - 8/18 11AM
George Duncan
gtduncan at gmail.com
Mon Aug 17 15:49:51 EDT 2020
---------- Forwarded message ---------
From: Graham Neubig <gneubig at cs.cmu.edu>
Date: Mon, Aug 17, 2020 at 11:56 AM
Subject: Re: Talk Announcment: Aida Nematzadeh (DeepMind) - 8/18 11AM
To: <lti-seminar at cs.cmu.edu>, <ml-faculty at cs.cmu.edu>, <
ml-phd-students at cs.cmu.edu>
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 <gneubig at cs.cmu.edu> 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.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://redfish.com/pipermail/friam_redfish.com/attachments/20200817/ec70ae69/attachment.html>
More information about the Friam
mailing list