University of Cambridge > Talks.cam > Language Technology Lab Seminars > Quantifying Linguistic Variation

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

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

ℹ️ Information

Quantifying Linguistic Variation

Download to your calendar using vCal

If you have a question about this talk, please contact Panagiotis Fytas .

Variation in language is ubiquitous, but difficult to define. Starting from Natural Language Processing’s more pragmatic definition that an increase in distributional shift leads to decreases in transferability, we search for quantitative measures of linguistic variation. By identifying subspaces in latent representations which relate to specific syntactic and semantic features, we attempt to disentangle interpretable dimensions of variation. This segmentation allows us to identify suitable data for transfer learning in specialized low-resource scenarios as well as to accurately evaluate the robustness of pre-trained models before fine-tuning them.

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

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Basement Seminar Room, Department of Zoology , Downing Street, CB2 3EJ Online via zoom & Kings Hedges Room Cambridge Science Festival - Big Data: The missing link

Other talks

Title TBC Title TBC Thelocactus Sheref Mansy, topic TBA Science & the Public in Action: Can and should climate scientists be activists? Title to be confirmed
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity