University of Cambridge > Talks.cam > NLIP Seminar Series > Generalised measures of predictive uncertainty in online language processing

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹ️ Information

Generalised measures of predictive uncertainty in online language processing

Download to your calendar using vCal

If you have a question about this talk, please contact Suchir Salhan .

I will present a family of sampling-based uncertainty measures that generalise surprisal and allow expressing a wider range of hypotheses about the workings of incremental language processing. I will show how these uncertainty measures, estimated via Monte Carlo sampling with neural network language models, exhibit predictive power comparable or superior to surprisal for a range of human neural and behavioural responses to incremental linguistic input.

Speaker Bio: Mario Giulianelli is an Associate Professor of Computational Linguistics at UCL , Director of the UCL Computational Linguistics Master’s programme, and a Member of the European Laboratory for Learning and Intelligent Systems. His research explores the information processing principles underlying the ability to understand, produce, learn, and use language in interaction—both in human and in artificial language processing systems.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Biffen Lecture Theatre, Genetics, Department of ChemSoc - Cambridge Chemistry Society Hodgkin-Huxley Seminat Room, Physiology Building

Other talks

Necessary mechanisms for super AI and stopping hallucinations: The consistent reasoning paradox and the indeterminacy function Talk TBC Title TBC Title to be confirmed The Jiangmen Underground Neutrino Observatory (JUNO): Status and First Physics Results The United States of America at 250: Reflections on the Past, Present and Future of Independence
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity