BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Reality Check: NLP in the era of Large Language Models - Vered Shw
 artz (University of British Columbia)
DTSTART:20230512T150000Z
DTEND:20230512T160000Z
UID:TALK200026@talks.cam.ac.uk
CONTACT:Michael Schlichtkrull
DESCRIPTION:Abstract:\n\nLLMs contributed to a major breakthrough in NLP\,
  both in terms of understanding natural language queries\, commands or que
 stions\; and in generating relevant\, coherent\, grammatical\, human-like 
 text. LLMs like ChatGPT became a product used by many\, for getting advice
 \, writing essays\, troubleshooting and writing code\, creative writing\, 
 and more. This calls for a reality check: which NLP tasks did LLMs solve? 
 What are the remaining challenges\, and which new opportunities did LLMs c
 reate?\n\n\nIn this talk\, I will discuss several areas of NLP that can be
 nefit from but are still challenging for LLMs: grounding\, i.e. interpreti
 ng language based on non-linguistic context\; reasoning\; and real-world a
 pplications. Finally\, I will argue that the standard benchmarking and eva
 luation techniques used in NLP need to drastically change in order to prov
 ide a more realistic picture of current capabilities.\n\nBio:\n\nVered Shw
 artz is an Assistant Professor of Computer Science at the University of Br
 itish Columbia\, and a CIFAR AI Chair at the Vector Institute. Her researc
 h in natural language processing focuses on commonsense reasoning\, comput
 ational semantics and pragmatics. Previously\, Vered was a postdoctoral re
 searcher at the Allen Institute for AI (AI2) and the University of Washing
 ton\, and received her PhD in Computer Science from Bar-Ilan University. V
 ered's work has been recognized with several awards\, including The Eric a
 nd Wendy Schmidt Postdoctoral Award for Women in Mathematical and Computin
 g Sciences\, the Clore Foundation Scholarship\, and an ACL 2016 outstandin
 g paper award.\n\n\nTopic: NLIP Seminar Time: May 12\, 2023 16:00 PM Londo
 n\n\nJoin Zoom Meeting https://cl-cam-ac-uk.zoom.us/j/94330375053?pwd=TjRt
 bTg5aUdzWVdLRU15RjR0V2g0Zz09\n\nMeeting ID: 943 3037 5053 Passcode: 768471
LOCATION:Virtual (Zoom)
END:VEVENT
END:VCALENDAR