Neural Search Talks β€” Zeta Alpha cover image

ColBERT + ColBERTv2: late interaction at a reasonable inference cost

Neural Search Talks β€” Zeta Alpha

00:00

The Differences Between Dance Retrieval and Crossing Coders

Colbert is precisely strong like you were saying out of domain or kind of like this kind of transfer when compared to the N2G. It's unclear why, but one clear difference is that it has a vector per term. So maybe something about anchoring it to the term level is more robust.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app