BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Zero-Shot Cross-lingual Transfer for XNLU - Milan Gritta\, Huawei 
 Noah’s Ark Lab
DTSTART:20220317T110000Z
DTEND:20220317T120000Z
UID:TALK171620@talks.cam.ac.uk
CONTACT:Marinela Parovic
DESCRIPTION:Task-oriented personal assistants enable people to interact wi
 th a host of devices and services using natural language. One of the chall
 enges of making neural dialogue systems available to more users is the lac
 k of training data for all but a few languages. Zero-shot methods try to s
 olve this issue by acquiring task knowledge in a high-resource language su
 ch as English with the aim of transferring it to the low-resource language
 (s). I will present two ACL papers from ’21 and ’22 that propose a few
  novel methods for this application/purpose.
LOCATION:GR06/07\, English Faculty\, 9 West Road (Sidgwick Site)
END:VEVENT
END:VCALENDAR