BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Unsupervised Domain Adaptation for Neural Search - Nils Reimers\, 
 HuggingFace
DTSTART:20220203T110000Z
DTEND:20220203T120000Z
UID:TALK168368@talks.cam.ac.uk
CONTACT:Marinela Parovic
DESCRIPTION:After textual information retrieval has stalled for many years
 \, pre-trained transformer networks gave a big performance boost resulting
  in extremely better search results.  However\, so far these approaches re
 quire large amount of training data which is seldom available for many use
 -cases. In this talk\, I will start with an overview of different neural s
 earch approach. I will then present BEIR\, a benchmark that test neural se
 arch methods in an out-of-domain setting. As the benchmark reveals\, many 
 architecture are sensitive to domain shifts limiting their usefulness for 
 many real word applications. To overcome this short-coming\, we created Ge
 nerative Pseudo Labeling (GPL)\, a method that transfers knowledge from sl
 ow\, but robust architectures\, to fast but domain-sensitive approaches\, 
 which results in highly improved search quality.
LOCATION:https://cam-ac-uk.zoom.us/j/97599459216?pwd=QTRsOWZCOXRTREVnbTJBd
 XVpOXFvdz09
END:VEVENT
END:VCALENDAR