BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : Situated Learning and Understanding of Natural Lan
 guage
DTSTART:20150219T101500
DTEND:20150219T113000
DTSTAMP:20260407T025946Z
UID:546a25fa05d577193b2b3196aa76675ae964240c3bff534e10c26d2b
CATEGORIES:Conferences - Seminars
DESCRIPTION:By : Yoav Artzi - University of Washington\nIC Faculty candida
 teAbstract :\nRobust language understanding systems have the potential to 
 transform how we interact with computers. However\, significant challenges
  in automated reasoning and learning remain to be solved before we achieve
  this goal. To accurately interpret user utterances\, for example when ins
 tructing a robot\, a system must jointly reason about word meaning\, gramm
 atical structure\, conversation history and world state. Additionally\, to
  learn without prohibitive data annotation costs\, systems must automatica
 lly make use of weak\, situated linguistic cues for autonomous language le
 arning.\nIn this talk\, I will present a framework that uses situated inte
 ractions to learn to map sentences to rich\, logical meaning representatio
 ns. The approach jointly induces the structure of a complex natural langua
 ge grammar and estimates its parameters\, while relying on various learnin
 g cues\, such as easily gathered demonstrations and even raw conversations
  without any additional annotation effort. It achieves state-of-the-art pe
 rformance on a number of tasks\, including robotic interpretation of navig
 ational directions and learning to understand user utterances in dialog sy
 stems. Such an approach\, when integrated into complete systems\, has the 
 potential to achieve continuous\, autonomous learning by participating in 
 actual interactions with users.Bio :\nYoav Artzi is a Ph.D. candidate in t
 he Computer Science & Engineering department at the University of Washingt
 on\, Seattle. His research interests are in the intersection of natural la
 nguage processing and machine learning. In particular\, he focuses on desi
 gning latent variable learning algorithms that recover rich representation
 s of linguistic meaning for situated natural language understanding. He co
 mpleted a B.Sc. summa cum laude in Computer Science in Tel Aviv University
 \, and is a recipient of the 2014 Microsoft Research PhD Fellowship and th
 e 2012 Yahoo Key Scientific Challenge award.More information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR