BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Machine Translation - Anoushka Mazumdar\, Churchill College
DTSTART:20210310T190000Z
DTEND:20210310T193000Z
UID:TALK158167@talks.cam.ac.uk
CONTACT:Matthew Ireland
DESCRIPTION:Sequence prediction is a popular machine learning task\, consi
 sting of making predictions about future symbols based on a previously obs
 erved sequence. This makes it ideal for NLP tasks such as machine translat
 ion\, where the ordering of the symbols (words) affects the meaning of the
  text.  \n\nIn this talk we will look at how sequence-to-sequence models c
 an be emulated using the Encoder-Decoder architecture. This approach will 
 involve two recurrent neural networks\, one to encode the input sequence (
 Encoder) and the other to decode the encoded input sequence into the targe
 t sequence (Decoder). We will then consider how this model can be applied 
 to machine translation\, and some other common use cases.
LOCATION:Online\, via MS Teams
END:VEVENT
END:VCALENDAR