BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Jointly Learning Syntax and Semantics - Jean Maillard\, NLIP\, Uni
 versity of Cambridge
DTSTART:20180302T120000Z
DTEND:20180302T130000Z
UID:TALK100351@talks.cam.ac.uk
CONTACT:Andrew Caines
DESCRIPTION:I will be presenting my work on latent tree sentence embedding
  models. These recurrent neural networks learn to induce binary parse tree
 s\, and at the same time use them to interpret a sentence. This is achieve
 d by incorporating a differentiable parser into the model\, optimised join
 tly with a Tree-LSTM composition function.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR