BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning across Adverse Conditions in Natural Language Processing 
 - Barbara Plank\, IT University of Copenhagen
DTSTART:20210527T100000Z
DTEND:20210527T110000Z
UID:TALK160813@talks.cam.ac.uk
CONTACT:Marinela Parovic
DESCRIPTION:Transferring knowledge to solve a related problem and learning
  from limited\, unreliable inputs are examples of extraordinary human abil
 ity. State-of-the-art machine learning models based on deep learning often
  fail under such adverse conditions. How can we build Natural Language Pro
 cessing technology which transfer better to new conditions\, such as learn
 ing to process a new language or a new text domain? Transfer learning (TL)
  and multi-task learning (MTL) can help remedy this problem. In this talk\
 , I will discuss TL and MTL methods to tackle this challenge and present s
 ome of our (on-going) work on NLP for zero-shot and few-shot transfer\, in
 cluding Danish\, a case study on a very low-resource dialect and recent wo
 rk on information extraction for task-oriented dialogue.
LOCATION:https://cam-ac-uk.zoom.us/j/97599459216?pwd=QTRsOWZCOXRTREVnbTJBd
 XVpOXFvdz09
END:VEVENT
END:VCALENDAR