BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal iCal API//EN
X-WR-CALNAME:Events items teaser
X-WR-TIMEZONE:America/Toronto
BEGIN:VTIMEZONE
TZID:America/Toronto
X-LIC-LOCATION:America/Toronto
BEGIN:DAYLIGHT
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
DTSTART:20180311T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20171105T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:69c233abd2656
DTSTART;TZID=America/Toronto:20180803T110000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20180803T110000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/masters-thesi
 s-presentation-simple-convolutional-neural
LOCATION:DC - William G. Davis Computer Research Centre 200 University Aven
 ue West 2310 Waterloo ON N2L 3G1 Canada
SUMMARY:Master’s Thesis Presentation: Simple Convolutional Neural Network
 s\nwith Linguistically-Annotated Input for Answer Selection in Question\nA
 nswering
CLASS:PUBLIC
DESCRIPTION:Royal Sequiera\, Master’s candidate\nDavid R. Cheriton School
  of Computer Science\n\nWith the advent of deep learning methods\, researc
 hers are abandoning\ndecades-old work in Natural Language Processing (NLP)
 . The research\ncommunity has been increasingly moving away from otherwise
  dominant\nfeature engineering approaches\; rather\, it is gravitating tow
 ards more\ncomplicated neural architectures. Highly competitive tools like
 \nParts-of-Speech taggers that exhibit human-like accuracy are traded\nfor
  complex networks\, with the hope that the neural network will learn\nthe 
 features needed. In fact\, there have been efforts to do NLP \"from\nscrat
 ch\" with neural networks that altogether eschew featuring\nengineering ba
 sed tools (Collobert _et al_.\, 2011).
DTSTAMP:20260324T064811Z
END:VEVENT
END:VCALENDAR