BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: Neuro-symbolic Representations  for Commonsense K
 nowledge  and Reasoning
DTSTART:20200302T101500
DTEND:20200302T111500
DTSTAMP:20260510T042405Z
UID:c65324faf01ccebd68b6b1f8b30da67ac35873b26d316b034840c4c1
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Antoine Bosselut - University of Washington\nIC Faculty ca
 ndidate\n\nAbstract:\nSituations described using natural language are rich
 er than what humans explicitly communicate. For example\, the sentence "Sh
 e pumped her fist" connotes many potential auspicious causes. For machines
  to understand natural language\, they must be able to reason about the co
 mmonsense inferences that underlie explicitly stated information. In this 
 talk\, I will present work on combining traditional symbolic knowledge and
  reasoning techniques with modern neural representations to endow machines
  with these capacities.\n\nFirst\, I will describe COMET\, an approach for
  learning commonsense knowledge about unlimited situations and concepts us
 ing transfer learning from language to knowledge. Second\, I will demonstr
 ate how these neural knowledge representations can dynamically construct s
 ymbolic graphs of contextual commonsense knowledge\, and how these graphs 
 can be used for interpretable\, generalized reasoning. Finally\, I will di
 scuss future research directions on conceptualizing NLP as commonsense sim
 ulation\, and the impact of this framing on difficult open-ended tasks suc
 h as story generation and dialogue.\n\nBio:\nAntoine Bosselut is a PhD Stu
 dent at the University of Washington advised by Professor Yejin Choi\, and
  a student researcher at the Allen Institute for Artificial Intelligence. 
 His research focuses on building systems for commonsense knowledge represe
 ntation and reasoning that combine the strengths of modern neural and trad
 itional symbolic methods. He was previously a student researcher on the De
 ep Learning team at Microsoft Research from 2017 to 2018.\n\nMore informat
 ion
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR
