优化超块剪枝策略，提升稀疏检索效率。
Efficiency Optimizations for Superblock-based Sparse Retrieval
- 提出简单有效的超块剪枝方法，降低评分计算开销。
- 在MS MARCO和BEIR数据集上保持良好相关性。
- 适合需要高效检索的多模型、多数据场景。
学习型稀疏检索（LSR）因其结合语言模型语义匹配与高效的CPU友好算法，成为第一阶段检索的流行方法。以往工作将块聚合为“超块”，通过先进剪枝启发式快速跳过查询处理中的块访问。本文提出一种简单而有效的超块剪枝方案，在降低超块得分计算开销的同时，保持了竞争性的相关性。该方案与紧凑索引结构及鲁棒的零样本配置相结合，适用于多种LSR模型和多个数据集。本文在MS MARCO和BEIR数据集上提供了分析论证与评估，表明该方案可作为高效稀疏检索的有力替代方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。