Document Reordering for Efficient Dynamic Pruning in Traditional and Learned Sparse Retrieval

Large scale Web search engines conduct first-stage retrieval using a traditional inverted index, on which they are expected to execute billions of queries on a very tight budget, i.e., less than 200 milliseconds. During query processing, the postings lists corresponding to each query term are traver...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Erman Yafay, Ismail Sengor Altingovde
Format:	Artigo
Jezik:	Inglês
Izdano:	IEEE 2026-01-01
Serija:	IEEE Access
Teme:	Information retrieval neural retrieval dynamic pruning inverted index search engines
Online dostop:	https://ieeexplore.ieee.org/document/11510186/
Oznake:	Označite Brez oznak, prvi označite!