Grammarly AI/NLP Club #10: Information-Theoretic Probing with Minimum Description Length
Speaker: Elena Voita, a Ph.D. student at the University of Edinburgh and the University of Amsterdam
Who will be interested: We will discuss enhanced ways of measuring what the BERT and ELMo models can learn. The talk will be of particular interest to people trying to use pre-trained models in practice, as well as to people with a more general interest in model analysis and/or representation learning. Attendees will get the most out of this talk if they have an awareness of these popular pre-trained models and understand their usefulness for downstream tasks.

When: Thursday, July 23 at 6:30 p.m.
Where: Online
Language: English

The event is free with mandatory registration. Please look out for a confirmation email with all the necessary information and links to online streaming.

More details: https://www.facebook.com/events/203520970979696/

Sign in to Google to save your progress. Learn more
Full Name (Name and Surname) *
E-mail *
Required to confirm your registration.
What is your area of expertise? *
What is your professional level? *
How did you find out about this event? *
Why are you interested in this topic? *
I would like to receive emails about upcoming AI & NLP events at Grammarly.
This possibility is optional. We promise you will receive only relevant information regarding Grammarly events hosted by recognized experts in AI & NLP from Ukraine and abroad.
Link to your LinkedIn or GitHub profile *
*
Required
Submit
Clear form
Never submit passwords through Google Forms.
This form was created inside of Grammarly. Report Abuse
Google Forms