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

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.

 

© 2006-2020 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity