3

What is the state of the art on putting text samples into a latent space?

posted
by
Avatar
CanadaPlus@lemmy.sdf.org
in
Avatar
mltheory@lemmy.intai.tech
2 comments
hidereport
Sort:
HotTopControversialNewOld
Avatar
gmatkins@sh.itjust.works
2 points

Used to be Bert. Might still be Bert. Everybody likes Bert.

permalink
report
reply
Avatar
CanadaPlus@lemmy.sdf.orgOP
1 point
*

Wow. That’s pretty vintage and tiny by ML standards, but it looks like it is still relevant.

There’s also Phrase-BERT if you want an embedding of the whole phrase. What are some models for getting the things back out?

permalink
report
parent
reply

Machine Learning - Theory | Research

!mltheory@lemmy.intai.tech

Create post

Community stats

  • 1

    Monthly active users

  • 51

    Posts

  • 4

    Comments

Community moderators