BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Detect – Verify – Communicate: Combating Misinformation with M
 ore Realistic NLP - Iryna Gurevych\, TU Darmstadt
DTSTART:20220929T100000Z
DTEND:20220929T110000Z
UID:TALK180500@talks.cam.ac.uk
CONTACT:Panagiotis Fytas
DESCRIPTION:Dealing with misinformation is a grand challenge of the inform
 ation society directed at equipping the computer users with effective tool
 s for identifying and debunking misinformation. Current Natural Language P
 rocessing (NLP) including its fact-checking research fails to meet the exp
 ectations of real-life scenarios. In this talk\, we show why the past work
  on fact-checking has not yet led to truly useful tools for managing misin
 formation\, and discuss our ongoing work on more realistic solutions. NLP 
 systems are expensive in terms of financial cost\, computation\, and manpo
 wer needed to create data for the learning process. With that in mind\, we
  are pursuing research on detection of emerging misinformation topics to f
 ocus human attention on the most harmful\, novel examples. Automatic metho
 ds for claim verification rely on large\, high-quality datasets. To this e
 nd\, we have constructed two corpora for fact checking\, considering large
 r evidence documents and pushing the state of the art closer to the realit
 y of combating misinformation. We further compare the capabilities of auto
 matic\, NLP-based approaches to what human fact checkers actually do\, unc
 overing critical research directions for the future. To edify false belief
 s\, we are collaborating with cognitive scientists and psychologists to au
 tomatically detect and respond to attitudes of vaccine hesitancy\, encoura
 ging anti-vaxxers to change their minds with effective communication strat
 egies.
LOCATION:English Faculty Building\, second floor\, SR24
END:VEVENT
END:VCALENDAR