[elpalek]

What method/model are you using for sparse search?

[GeorgeCurtis]

We're going to use BM25. Currently it is just dense search. Coming very soon

[elpalek]

have you thought about SPALDE models? ex: https://arxiv.org/abs/2109.10086

[GeorgeCurtis]

Looks really interesting, I'll have a proper read. What would be your reasoning to incorporate this if we already have vector functionality and semantic search?

[elpalek]

my project deals w/ non-english text, bm25 performance is middeling. Language specific sparse model helps.

[xavcochran]

We will definitely look into it. The SPLADE models look promising!

[xavcochran]

SPALDE*