BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20220327T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20211031T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260405T225053Z
UID:1636556400@ist.ac.at
DTSTART:20211110T160000
DTEND:20211110T180000
DESCRIPTION:Speaker: Lena Voita\nhosted by Marco Mondelli\nAbstract: In the
  last decade\, machine translation shifted from traditional statistical ap
 proaches (SMT) to end-to-end neural ones (NMT). While traditional approach
 es split the translation task into several components and use various hand
 -crafted features\, NMT learns the translation task directly from data\, w
 ithout splitting it into subtasks. The main question of this talk is how N
 MT manages to do this\, and I will try to answer it keeping in mind the tr
 aditional paradigm. First\, I will show that NMT components can take roles
  corresponding to the features modelled explicitly in SMT. Then I will exp
 lain how NMT balances the two different types of context\, the source and 
 the prefix of the target sentence. Finally\, we will see that NMT training
  consists of the stages where it focuses on the competences mirroring thre
 e core SMT components: target-side language modeling\, lexical translation
 \, and reordering.
LOCATION:Zoom Link: https://istaustria.zoom.us/j/94284847467?pwd=VXlZZjhtTE
 pZbUpGRHBId3liM1k0UT09  Meeting ID: 942 8484 7467 Passcode: 719116\, ISTA
ORGANIZER:
SUMMARY:Lena Voita: Neural Machine Translation Inside Out
URL:https://talks-calendar.ista.ac.at/events/3407
END:VEVENT
END:VCALENDAR