Learned sparse models such as SPLADE have successfully shown how to incorporate the benefits of state-of-the-art neural information retrieval models into the classical inverted index data structure. Despite their improvements in effectiveness, learned sparse models are not as efficient as classical sparse model such as BM25. The problem has been investigated and addressed by recently developed strategies, such as guided traversal query processing and static pruning, with different degrees of success on in-domain and out-of-domain datasets. In this work, we propose a new query processing strategy for SPLADE based on a two-step cascade. The first step uses a pruned and reweighted version of the SPLADE sparse vectors, and the second step uses the original SPLADE vectors to re-score a sample of documents retrieved in the first stage. Our extensive experiments, performed on 30 different in-domain and out-of-domain datasets, show that our proposed strategy is able to improve mean and tail response times over the original single-stage SPLADE processing by up to $30\times$ and $40\times$, respectively, for in-domain datasets, and by 12x to 25x, for mean response on out-of-domain datasets, while not incurring in statistical significant difference in 60\% of datasets.

翻译：学习型稀疏模型（如SPLADE）已成功展示了如何将最先进的神经信息检索模型的优势融入经典倒排索引数据结构中。尽管在效果上有所提升，但学习型稀疏模型的效率仍不及BM25等经典稀疏模型。这一问题已通过近年来发展的策略（如引导式遍历查询处理与静态剪枝）得到研究并解决，但不同策略在域内与域外数据集上的成功程度存在差异。本文提出了一种基于两步级联的SPLADE查询处理新策略：第一步使用SPLADE稀疏向量的剪枝与重加权版本，第二步利用原始SPLADE向量对第一阶段检索的文档样本进行重新评分。我们在30个不同的域内与域外数据集上进行了广泛实验，结果显示，与原始单阶段SPLADE处理相比，所提策略在域内数据集上可将平均响应时间与尾部响应时间分别提升至多30倍与40倍，在域外数据集上平均响应时间提升12至25倍，且在60%的数据集上未出现统计显著差异。