BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Fact-checking as a conversation: an AI perspective - Dr Andreas Vl
 achos (University of Cambridge)
DTSTART:20231116T183000Z
DTEND:20231116T193000Z
UID:TALK202729@talks.cam.ac.uk
CONTACT:83221
DESCRIPTION:Misinformation is considered one of the major challenges of ou
 r times resulting in numerous efforts against it. Fact-checking\, the task
  of assessing whether a claim is true or false\, is considered a key in re
 ducing its impact. In the first part of this talk our speaker will present
  recent and ongoing work on automating this task using natural language pr
 ocessing\, moving beyond simply classifying claims as true or false in the
  following aspects: incorporating tabular information\, neurosymbolic infe
 rence\, and using a search engine as a source of evidence. In the second p
 art of this talk\, an alternative approach to combating misinformation wil
 l be presented via dialogue agents\, and present results on how internet u
 sers engage in constructive disagreements and problem-solving deliberation
 .\n\nAndreas Vlachos is a professor of Natural Language Processing and Mac
 hine Learning at the Department of Computer Science and Technology at the 
 University of Cambridge and a Dinesh Dhamija fellow of Fitzwilliam College
 . Current projects include dialogue modelling\, automated fact checking an
 d imitation learning. He has also worked on semantic parsing\, natural lan
 guage generation and summarization\, language modelling\, information extr
 action\, active learning\, clustering and biomedical text mining. His rese
 arch team is supported by grants from ERC\, EPSRC\, ESRC\, Facebook\, Amaz
 on\, Google\, Huawei\, the Alan Turing Institute and the Isaac Newton Trus
 t.
LOCATION:CUED. LR0
END:VEVENT
END:VCALENDAR