most citedOperational Advice for Dense and Sparse Retrievers: HNSW, Flat, or Inverted Indexes?

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.IRShow all

2 papers · 1 filter

cs.IR2024★ 1 cited

Operational Advice for Dense and Sparse Retrievers: HNSW, Flat, or Inverted Indexes?

Jimmy Lin

Practitioners working on dense retrieval today face a bewildering number of choices. Beyond selecting the embedding model, another consequential choice is the actual implementation…

cs.IR2023

Searching Dense Representations with Inverted Indexes

Jimmy Lin, Tommaso Teofili

Nearly all implementations of top- retrieval with dense vector representations today take advantage of hierarchical navigable small-world network (HNSW) indexes. However, the ge…