Dual Skipping Guidance For Document Retrieval With Learned Sparse Representations
Yifan Qiao, Yingrui Yang, Haixin Lin, Tianbo Xiong, Xiyue Wang, Tao Yang . Arxiv 2022 – 3 citations
[Paper]
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.