Current state-of-the-art document retrieval solutions mainly follow an index-retrieve paradigm, where the index is hard to be directly optimized for the final retrieval target. In this paper, we aim to show that an end-to-end deep neural network unifying training and indexing stages can significantly improve the recall performance of traditional methods. To this end, we propose Neural Corpus Indexer (NCI), a sequence-to-sequence network that generates relevant document identifiers directly for a designated query. To optimize the recall performance of NCI, we invent a prefix-aware weight-adaptive decoder architecture, and leverage tailored techniques including query generation, semantic document identifiers, and consistency-based regularization. Empirical studies demonstrated the superiority of NCI on two commonly used academic benchmarks, achieving +21.4% and +16.8% relative enhancement for Recall@1 on NQ320k dataset and R-Precision on TriviaQA dataset, respectively, compared to the best baseline method.

翻译：当前最先进的文档检索解决方案主要遵循“索引-检索”范式，其中索引难以直接针对最终的检索目标进行优化。在本文中，我们旨在证明一个统一训练和索引阶段的端到端深度神经网络能够显著提升传统方法的召回性能。为此，我们提出了神经语料库索引器（NCI），这是一种序列到序列网络，可直接为指定查询生成相关文档标识符。为了优化NCI的召回性能，我们设计了一种前缀感知的自适应权重解码器架构，并利用了定制的技术，包括查询生成、语义文档标识符和基于一致性的正则化。实证研究表明，在两个常用的学术基准测试上，NCI相较于最佳基线方法，分别在NQ320k数据集上的Recall@1和TriviaQA数据集上的R-Precision指标上实现了+21.4%和+16.8%的相对提升，展现了其优越性。