Dual Skipping Guidance for Document Retrieval with Learned Sparse Representations

04/23/2022

∙

by   Yifan Qiao, et al.

∙

0

∙

share

This paper proposes a dual skipping guidance scheme with hybrid scoring to accelerate document retrieval that uses learned sparse representations while still delivering a good relevance. This scheme uses both lexical BM25 and learned neural term weights to bound and compose the rank score of a candidate document separately for skipping and final ranking, and maintains two top-k thresholds during inverted index traversal. This paper evaluates time efficiency and ranking relevance of the proposed scheme in searching MS MARCO TREC datasets.