A statistical risk estimation method enables query-specific dimension selection in dense embeddings, achieving equivalent effectiveness with about 50% smaller embeddings at inference time.
InFindings of the Association for Computational Linguistics: ACL- IJCNLP 2021, pages 3392–3405, Online
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Statistical Foundations of DIME: Risk Estimation for Practical Index Selection
A statistical risk estimation method enables query-specific dimension selection in dense embeddings, achieving equivalent effectiveness with about 50% smaller embeddings at inference time.