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 Neural Information Retrieval

There's a lot of interesting ramifications. What do you make out of all of these space and where are you more particularly more personally interested in looking into in your own interests? Where do you think that most of the low hanging fruit is going to come from in the next year or two? Yeah. I mean, I think they're all interesting. Because cross encoders were around first, there's probably much less low hanging fruit there. But I mean, this is clearly the most well studied. The least studied is like the learn sparse retrieval,. Like this, the splayed, learn something to put an inverted index.

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