University of Cambridge > Talks.cam > Microsoft Research Cambridge, public talks > Deep (Inter-)Active Learning for NLP: Cure-all or Catastrophe?

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

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

Deep (Inter-)Active Learning for NLP: Cure-all or Catastrophe?

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins.

Please note, this event may be recorded. Microsoft will own the copyright of any recording and reserves the right to distribute it as required.

While deep learning produces supervised models with unprecedented predictive performance on many tasks, under typical training procedures, advantages over classical methods emerge only with large datasets. The extreme data-dependence of reinforcement learners may be even more problematic. Millions of experiences sampled from video-games come cheaply, but human-interacting systems can’t afford to waste so much labor. In this talk, I will discuss several efforts to increase the labor-efficiency of learning from human interactions. Specifically, I will cover work on learning dialogue policies, deep active learning for natural language processing, learning from noisy and singly-labeled data, and active learning with partial feedback. Finally, time permitting, I’ll discuss a new approach for reducing the reliance of NLP models on spurious associations in the data that relies on a new mechanism for interacting with annotators.

This talk is part of the Microsoft Research Cambridge, public talks series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Evolution and Development Seminar Series CUSynBioSoc Trust and Cloud Computing

Other talks

Materials, Membranes and Motivations for Research Bridging the Gap: writing commentaries on the Dead Sea scrolls in the 21st century CANCELLED gloknos Annual Lecture – Prof Sarah de Rijcke TBC A novel mechanosensor in the endothelium that regulates the site-specific distribution of atherosclerosis St Catharine's Political Economy Seminar Series - Terry Barker 'The institutional capture of IPCC economics by neoclassical ideology' Climate, Carbon, and Computer Science
 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity