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:20190310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20181104T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:69b23055b7d3c
DTSTART;TZID=America/Toronto:20190405T100000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20190405T100000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/masters-thesi
 s-presentation-end-end-neural-information
LOCATION:DC - William G. Davis Computer Research Centre 200 University Aven
 ue West 3317 Waterloo ON N2L 3G1 Canada
SUMMARY:Master’s Thesis Presentation: End-to-end Neural Information\nRetr
 ieval
CLASS:PUBLIC
DESCRIPTION:WEI YANG\, MASTER’S CANDIDATE\n_David R. Cheriton School of C
 omputer Science_\n\nIn recent years\, we have witnessed many successes of 
 neural networks\nin the information retrieval community with lots of label
 ed data. Yet\nit remains unknown whether the same techniques can be easily
  adapted\nto search social media posts where the text is much shorter. In\
 naddition\, we find that most neural information retrieval models are\ncom
 pared against weak baselines. \n\nIn this thesis\, we build an end-to-end
  neural information retrieval\nsystem using two toolkits: Anserini and Mat
 chZoo. In addition\, we also\npropose a novel neural model to capture the 
 relevance of short and\nvaried tweet text\, named MP-HCNN. 
DTSTAMP:20260312T031741Z
END:VEVENT
END:VCALENDAR