BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Document Summarisation: Modelling\, Datasets and Verification of C
 ontent - Shay Cohen\, University of Edinburgh
DTSTART:20211111T110000Z
DTEND:20211111T120000Z
UID:TALK165679@talks.cam.ac.uk
CONTACT:Marinela Parovic
DESCRIPTION:Within Natural Language Processing\, document summarisation is
  one of the central problems. It has both short-term societal implications
  and long-term implications in terms of the success of AI. I will describe
  advances made in this area with respect to three different aspects: metho
 dology and modelling\, dataset development and enforcing factuality of sum
 maries. In relation to modelling\, I will show how reinforcement learning 
 can be used to directly maximise the metric by which the summaries are bei
 ng evaluated. With regards to dataset development\, I will describe a data
 set that we released for summarisation\, XSum\, in which a single sentence
  is used to describe the content of a whole article. The dataset has becom
 e a standard benchmark for summarisation. Finally\, in relation to factual
 ity\, I will show how one can improve the quantitative factuality of summa
 ries by re-ranking them in a beam based on a "verification" model.
LOCATION:https://cam-ac-uk.zoom.us/j/97599459216?pwd=QTRsOWZCOXRTREVnbTJBd
 XVpOXFvdz09
END:VEVENT
END:VCALENDAR