Passage reranking is a crucial task in many applications, particularly when dealing with large-scale documents. Traditional neural architectures are limited in retrieving the best passage for a question because they usually match the question to each passage separately, seldom considering contextual information in other passages that can provide comparison and reference information. This paper presents a list-context attention mechanism to augment the passage representation by incorporating the list-context information from other candidates. The proposed coarse-to-fine (C2F) neural retriever addresses the out-of-memory limitation of the passage attention mechanism by dividing the list-context modeling process into two sub-processes, allowing for efficient encoding of context information from a large number of candidate answers. This method can be generally used to encode context information from any number of candidate answers in one pass. Different from most multi-stage information retrieval architectures, this model integrates the coarse and fine rankers into the joint optimization process, allowing for feedback between the two layers to update the model simultaneously. Experiments demonstrate the effectiveness of the proposed approach.

翻译：段落重排序是许多应用中的关键任务，特别是在处理大规模文档时。传统神经架构在检索问题的最优段落方面存在局限性，因为它们通常将问题与每个段落单独匹配，很少考虑其他段落中能提供比较和参考信息的上下文线索。本文提出一种列表上下文注意力机制，通过整合来自其他候选项的列表上下文信息来增强段落表示。所提出的粗到细神经检索器通过将列表上下文建模过程划分为两个子过程，解决了段落注意力机制的显存不足限制，从而能够高效地对大量候选项的上下文信息进行编码。该方法可通用地用于一次性编码任意数量候选项的上下文信息。与多数多阶段信息检索架构不同，该模型将粗排序器和细排序器整合到联合优化过程中，允许两层之间通过反馈同时更新模型。实验证明了该方法的有效性。