BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards Trustworthy Natural Language Processing - Jasmijn Bastings
  (Google Brain)
DTSTART:20221118T120000Z
DTEND:20221118T130000Z
UID:TALK192332@talks.cam.ac.uk
CONTACT:Michael Schlichtkrull
DESCRIPTION:Abstract:\n\nRecent NLP models can achieve incredibly high acc
 uracies\, but how do we know whether we can trust them\, or whether they a
 re trustworthy? First we will establish what these terms mean\, and what t
 he umbrella of trustworthy NLP covers. We'll then discuss what desiderata 
 a trustworthy NLP system should meet\, before we look at recent work done 
 at Google towards this end\, touching on the topics of interpretability\, 
 privacy and robustness.\n\nBio:\n\nJasmijn Bastings (she/her) is a researc
 her at Google Brain Amsterdam\, having joined Google in Berlin late 2019. 
 She holds a PhD from ILLC\, University of Amsterdam\, on the topic of Inte
 rpretable and Linguistically-informed Deep Learning for NLP. Recently\, Ja
 smijn has been focusing on explainability\, privacy and robustness. She is
  also one of the organizers of BlackBoxNLP: Analyzing and interpreting neu
 ral networks for NLP\, a workshop co-located with EMNLP 2022.\n\nTopic: NL
 IP Seminar\nTime: Nov 18\, 2022 12:00 PM London\n\nJoin Zoom Meeting\nhttp
 s://cl-cam-ac-uk.zoom.us/j/91073515866?pwd=UnJmTER6dmZLeWpPOUo0VUJBOGxYQT0
 9\n\nMeeting ID: 910 7351 5866\nPasscode: 646960\n\n
LOCATION:Virtual (Zoom)
END:VEVENT
END:VCALENDAR