← Back to context Comment by GeorgeCurtis 2 days ago We're going to use BM25. Currently it is just dense search. Coming very soon 5 comments GeorgeCurtis Reply elpalek 2 days ago have you thought about SPALDE models? ex: https://arxiv.org/abs/2109.10086 GeorgeCurtis 2 days ago 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 2 days ago my project deals w/ non-english text, bm25 performance is middeling. Language specific sparse model helps. 2 replies →
elpalek 2 days ago have you thought about SPALDE models? ex: https://arxiv.org/abs/2109.10086 GeorgeCurtis 2 days ago 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 2 days ago my project deals w/ non-english text, bm25 performance is middeling. Language specific sparse model helps. 2 replies →
GeorgeCurtis 2 days ago 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 2 days ago my project deals w/ non-english text, bm25 performance is middeling. Language specific sparse model helps. 2 replies →
elpalek 2 days ago my project deals w/ non-english text, bm25 performance is middeling. Language specific sparse model helps. 2 replies →
have you thought about SPALDE models? ex: https://arxiv.org/abs/2109.10086
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?
my project deals w/ non-english text, bm25 performance is middeling. Language specific sparse model helps.
2 replies →