University of Cambridge > Talks.cam > Language Technology Lab Seminars > Zero-Shot Cross-lingual Transfer for XNLU

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

Zero-Shot Cross-lingual Transfer for XNLU

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Marinela Parovic.

Task-oriented personal assistants enable people to interact with a host of devices and services using natural language. One of the challenges of making neural dialogue systems available to more users is the lack of training data for all but a few languages. Zero-shot methods try to solve this issue by acquiring task knowledge in a high-resource language such 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.

This talk is part of the Language Technology Lab Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Exam Practice Guide Special DPMMS Colloquium Clinicians meet STEM Scientists

Other talks

Transversals in quasirandom latin squares Improved assessment of the statistical stability of turbulent flows using extended Orr-Sommerfeld stability analysis Jenny Bangham: “Blood, race and transfusion: Fisher’s work with the wartime Galton Serum Unit” The long road of building a nervous system - smooth travels and accidents on the journey to get the shape and size. JUNE - an individual based model A network of invariant solutions underlying spatio-temporal patterns in inclined layer convection
 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity