arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.02883cs.IR
收藏

基于超块的稀疏检索效率优化

Efficiency Optimizations for Superblock-based Sparse Retrieval

University of California, Santa Barbara(加州大学圣塔芭芭拉分校)

Parker Carlson, Wentai Xie, Rohil Shah, Tao Yang

AI总结:

本文提出了一种高效的超块剪枝方案,结合紧凑索引和零样本配置,以提升稀疏检索的效率和相关性。

摘要:

已学习稀疏检索(LSR)是一种流行的第一阶段检索方法,因为它结合了语言模型的语义匹配与高效的CPU友好算法。先前的工作将块聚合为“超块”,通过使用先进的剪枝启发式方法,在查询处理过程中快速跳过块的访问。本文提出了一种简单而有效的超块剪枝方案,该方案在保持竞争相关性的同时减少了超块得分计算的开销。它将此方案与紧凑的索引结构和稳健的零样本配置相结合,后者在多种LSR模型和数据集上均有效。本文在MS MARCO和BEIR数据集上提供了分析论证和评估,证明所提出的方案可以成为高效稀疏检索的强大替代方案。

英文摘要:

Learned sparse retrieval (LSR) is a popular method for first-stage retrieval because it combines the semantic matching of language models with efficient CPU-friendly algorithms. Previous work aggregates blocks into "superblocks" to quickly skip the visitation of blocks during query processing by using an advanced pruning heuristic. This paper proposes a simple and effective superblock pruning scheme that reduces the overhead of superblock score computation while preserving competitive relevance. It combines this scheme with a compact index structure and a robust zero-shot configuration that is effective across LSR models and multiple datasets. This paper provides an analytical justification and evaluation on the MS MARCO and BEIR datasets, demonstrating that the proposed scheme can be a strong alternative for efficient sparse retrieval.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑