BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//bbuzz22//speaker//DULSC8
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-bbuzz22-E9AJJE@pretalx.com
DTSTART;TZID=CET:20220614T145000
DTEND;TZID=CET:20220614T153000
DESCRIPTION:Sentiment-to-Sentiment translation is a special case for Style 
 Transfer. Style Transfer is emphasised on generating the opposite polar st
 yle in terms of emotions or sentiment. This results in the transfer of sty
 le successfully but loses the semantic context of the sentence. This is ca
 used due to inefficient amount of data having these relevant paired senten
 ces with polar styles. This talk focuses on generating unpaired dataset wh
 ich preserves the semantic context during a style change using cycled Rein
 forcement Learning approach on parallel data having emotionalization and n
 eutralization modules. \n\nThe talk can be viewed from https://bit.ly/bbuz
 z2022
DTSTAMP:20260612T235603Z
LOCATION:Maschinenhaus
SUMMARY:Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement
  Learning Approach - Sakshi Deo Shukla
URL:https://pretalx.com/bbuzz22/talk/E9AJJE/
END:VEVENT
END:VCALENDAR