Neural Search Talks — Zeta Alpha cover image

ColBERT + ColBERTv2: late interaction at a reasonable inference cost

Neural Search Talks — Zeta Alpha

00:00

The Future of Dense Retrieval Models

In domain, it's pretty competitive with other methods out of domain. It seems to be better than single vector, denser, trivial. These are the methods that work well in the generalization. So I'm curious about what will happen here, but I don't know.

Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner