BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Multimodal natural language processing: when text is not enough - 
 Lucia Specia (Imperial College London)
DTSTART:20191018T110000Z
DTEND:20191018T120000Z
UID:TALK128491@talks.cam.ac.uk
CONTACT:James Thorne
DESCRIPTION:In this talk I will provide an overview of work on multimodal 
 machine learning\, where visual information is used to build richer contex
 t models for natural language tasks. Most of the talk will be focused on  
 approaches to machine translation that exploit both textual and visual inf
 ormation to deal with complex linguistic ambiguities as well as common lin
 guistic biases. I will cover state of the art approaches and their limitat
 ions and describe a number of studies on whether and when visual informati
 on can be beneficial to the task.   
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR