BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:NLIP Seminar Series
SUMMARY:Towards explainable fact checking - Isabelle Augen
 stein (University of Copenhagen)
DTSTART;TZID=Europe/London:20200619T120000
DTEND;TZID=Europe/London:20200619T130000
UID:TALK142264AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/142264
DESCRIPTION:Automatic fact checking is one of the more involve
 d NLP tasks currently researched: not only does it
  require sentence understanding\, but also an unde
 rstanding of how claims relate to evidence documen
 ts and world knowledge. Moreover\, there is still 
 no common understanding in the automatic fact chec
 king community of how the subtasks of fact checkin
 g — claim check-worthiness detection\, evidence re
 trieval\, veracity prediction — should be framed. 
 This is partly owing to the complexity of the task
 \, despite efforts to formalise the task of fact c
 hecking through the development of benchmark datas
 ets.\nThe first part of the talk will be on automa
 tically generating textual explanations for fact c
 hecking\, thereby exposing some of the reasoning p
 rocesses these models follow. The second part of t
 he talk will be on re-examining how claim check-wo
 rthiness is defined\, and how check-worthy claims 
 can be detected\; followed by how to automatically
  generate claims which are hard to fact-check auto
 matically.\n\n\nBio:\n\nIsabelle Augenstein is an 
 associate professor in Natural Language Processing
  and Machine Learning at the University of Copenha
 gen\, Department of Computer Science\, where she h
 ead the Copenhagen NLU research group. Her main re
 search interests are weakly supervised and low-res
 ource learning with applications including fact ch
 ecking\, question answering and cross-lingual lear
 ning.\n
LOCATION:https://meet.google.com/xkv-cako-arr
CONTACT:Guy Aglionby
END:VEVENT
END:VCALENDAR