University of Cambridge > Talks.cam > Language Technology Lab Seminars > Correlations Between Word Vector Sets

  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

ℹī¸ Information

Correlations Between Word Vector Sets

Download to your calendar using vCal

If you have a question about this talk, please contact Qianchu Liu .

A joint Leverhulme Centre for the Future of Intelligence (CFI) and Language Technology Lab (LTL) seminar on Human-Centric AI Technologies

Word embeddings are typically treated as vectors to allow for various geometric operations. We question their very nature and whether they are vectors at all. We propose an alternative, statistical perspective on these objects, leading to state-of-the-art similarity measures defined from elementary correlation coefficients.

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

Entertaining Room, Darwin College. Cambridge Judge Business School, W4.03 Jesus College Coleridge Room

Other talks

Title to be confirmed TOWARD AFFORDABLE PREVENTIVE HEALTHCARE: How basic science addresses grand challenges The Imagined Conflict: On Science and God Title to be confirmed Dinner Cambridge RNA Club - ONLINE
 

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