PLAID-PRF performs pseudo-relevance feedback by treating PLAID's indexing-time centroid codes as semantic terms, selecting diverse reconstructed token vectors to append to the query and rerunning PLAID.
Title resolution pending
1 Pith paper cite this work, alongside 2 external citations. Polarity classification is still indexing.
1
Pith paper citing it
2
external citations · OpenAlex
fields
cs.IR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PLAID-PRF: Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID
PLAID-PRF performs pseudo-relevance feedback by treating PLAID's indexing-time centroid codes as semantic terms, selecting diverse reconstructed token vectors to append to the query and rerunning PLAID.