BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Imitation learning\, zero-shot learning and automated fact checkin
 g - Andreas Vlachos\, NLIP\, University of Cambridge
DTSTART:20181005T110000Z
DTEND:20181005T120000Z
UID:TALK108106@talks.cam.ac.uk
CONTACT:Andrew Caines
DESCRIPTION:In this talk I will give an overview of my research in machine
  learning for natural language processing. I will begin by introducing my 
 work on imitation learning\, a machine learning paradigm I have used to de
 velop novel algorithms for structure prediction that have been applied suc
 cessfully to a number of tasks such as semantic parsing\, natural language
  generation and information extraction. Key advantages are the ability to 
 handle large output search spaces and to learn with non-decomposable loss 
 functions. Following this\, I will discuss my work on zero-shot learning u
 sing neural networks\, which enabled us to learn models that can predict l
 abels for which no data was observed during training. I will conclude with
  my work on automated fact-checking\, a challenge we proposed in order to 
 stimulate progress in machine learning\, natural language processing and\,
  more broadly\, artificial intelligence.\n
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR