Video wird geladen...
Video konnte nicht geladen werden
By now, everyone knows that single-vector embedding models are hugely limiting for modern workflows. But they contain than you think: you can extract sparse Latent Terms from them. And it turns out that BM25 is all you need to turn this vocabulary into a strong retriever.
39,603 Aufrufe • vor 11 Tagen •via X (Twitter)
0 Kommentare
Keine Kommentare verfügbar
Kommentare vom Original-Post werden hier angezeigt
