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

Correlations Between Word Vector Sets

Add to your list(s) 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.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2020 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity