BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards explainable fact checking - Prof. Isabelle Augenstein\, Un
 iversity of Copenhagen
DTSTART:20210128T110000Z
DTEND:20210128T120000Z
UID:TALK156460@talks.cam.ac.uk
CONTACT:Haim Dubossarsky
DESCRIPTION:Automatic fact checking is one of the more involved NLP tasks 
 currently researched: not only does it require sentence understanding\, bu
 t also an understanding of how claims relate to evidence documents and wor
 ld knowledge. Moreover\, there is still no common understanding in the aut
 omatic fact checking community of how the subtasks of fact checking — cl
 aim check-worthiness detection\, evidence retrieval\, veracity prediction 
 — should be framed. This is partly owing to the complexity of the task\,
  despite efforts to formalise the task of fact checking through the develo
 pment of benchmark datasets. This talk will re-examine how fact checking i
 s defined\, and present some of my recent work on training explainable fac
 t checking models to expose some of the reasoning processes these models f
 ollow.\n
LOCATION:https://cam-ac-uk.zoom.us/j/97599459216?pwd=QTRsOWZCOXRTREVnbTJBd
 XVpOXFvdz09
END:VEVENT
END:VCALENDAR