How to improve on BERT embeddings for long-form doc search
Ғылым және технология
Yext data scientists Michael Misiewicz and Allison Rossetto present "How to improve on BERT embeddings for long-form doc search" to a New York Natural Language Processing meetup audience, April 25, 2022, moderated by Seth Grimes.
For the NY NLP meetup, visit www.meetup.com/NY-NLP/.
Пікірлер: 4
segmentation part is not clear. Lookslike speaker is not intended to tell.
I think I still have the questions about merging cross products. From what I understand cross products between two vectors are only defined for three-dimensional vectors. Is there an extension to n dimensions? Is it something from differential geometry? Or are you talking about outer products?
Clifford algebras do high dimensional cross products.
ᴘʀᴏᴍᴏsᴍ