Sparse neural retrievers, such as DeepImpact, uniCOIL and SPLADE, have been introduced recently as an efficient and effective way to perform retrieval with inverted indexes. They aim to learn term importance and, in some cases, document expansions, to provide a more effective document ranking compared to traditional bag-of-words retrieval models such as BM25. However, these sparse neural retrievers have been shown to increase the computational costs and latency of query processing compared to their classical counterparts. To mitigate this, we apply a well-known family of techniques for boosting the efficiency of query processing over inverted indexes: static pruning. We experiment with three static pruning strategies, namely document-centric, term-centric and agnostic pruning, and we assess, over diverse datasets, that these techniques still work with sparse neural retrievers. In particular, static pruning achieves $2\times$ speedup with negligible effectiveness loss ($\leq 2\%$ drop) and, depending on the use case, even $4\times$ speedup with minimal impact on the effectiveness ($\leq 8\%$ drop). Moreover, we show that neural rerankers are robust to candidates from statically pruned indexes.

翻译：稀疏神经检索器（如DeepImpact、uniCOIL和SPLADE）近年来被引入，作为一种利用倒排索引实现高效且有效检索的方法。它们旨在学习词条重要性，并在某些情况下进行文档扩展，以提供比传统词袋检索模型（如BM25）更有效的文档排序。然而，与经典检索器相比，这些稀疏神经检索器已被证明会增加查询处理的计算成本和延迟。为缓解这一问题，我们应用了一类广为人知的技术——静态剪枝，用于提升倒排索引上查询处理的效率。我们实验了三种静态剪枝策略，即文档中心剪枝、词条中心剪枝和无关剪枝，并在多种数据集上评估了这些技术对稀疏神经检索器的适用性。特别地，静态剪枝在有效性损失可忽略（下降≤2%）的情况下实现了2倍加速，且根据具体用例，甚至能以最小有效性影响（下降≤8%）实现4倍加速。此外，我们证明神经重排序器对来自静态剪枝索引的候选项具有鲁棒性。