BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: Learning to Understand Entities In Text
DTSTART:20190325T101500
DTEND:20190325T111500
DTSTAMP:20260511T105427Z
UID:afe6adeb9fa937807b439a2810548ab82457832746302dda053c4993
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Eunsol Choi - University of Washington\nIC Faculty candida
 te\n\nAbstract:\nReal world entities such as people\, organizations and co
 untries play a critical role in text. Reading offers rich explicit and imp
 licit information about these entities\, such as the categories they belon
 g to\, relationships they have with other entities\, and events they parti
 cipate in. In this talk\, we introduce approaches to infer implied informa
 tion about entities\, and to automatically query such information in an in
 teractive setting. We expand the scope of information that can be learned 
 from text for a range of tasks\, including sentiment extraction\, entity t
 yping and question answering. To this end\, we introduce new ideas for how
  to find effective training data\, including crowdsourcing and large-scale
  naturally occurring weak supervision data. We also describe new computati
 onal models\, that represent rich social and conversation contexts to tack
 le these tasks. Together\, these advances significantly expand the scope o
 f information that can be incorporated into the next generation of machine
  reading systems.\n\nBio:\nEunsol Choi is a Ph.D candidate at the Paul G. 
 Allen School of Computer Science at the University of Washington. Her rese
 arch focuses on natural language processing\, specifically applying machin
 e learning to recover semantics from text. She completed a B.A. in Compute
 r Science and Mathematics at Cornell University\, and is a recipient of th
 e Facebook fellowship.\n\nMore information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR