Common IR pipelines are typically cascade systems that may involve multiple rankers and/or fusion models to integrate different information step-by-step. In this paper, we propose a novel re-ranker named Fusion-in-T5 (FiT5), which integrates document text information, retrieval features, and global document information into a single unified model using templated-based input and global attention. Experiments on passage ranking benchmarks MS MARCO and TREC DL show that FiT5 significantly improves ranking performance over prior pipelines. Analyses find that through global attention, FiT5 is able to jointly utilize the ranking features via gradually attending to related documents, and thus improve the detection of subtle nuances between them. Our code will be open-sourced.

翻译：常见的信息检索流水线通常是级联系统，可能涉及多个排序器和/或融合模型以逐步整合不同信息。本文提出一种新型重排序器Fusion-in-T5（FiT5），通过基于模板的输入和全局注意力机制，将文档文本信息、检索特征及全局文档信息统一整合至单一模型中。在段落排序基准MS MARCO和TREC DL上的实验表明，FiT5显著优于现有流水线的排序性能。分析发现，FiT5通过全局注意力能够逐步关注相关文档，从而联合利用排序特征，并提升对文档间细微差异的检测能力。我们的代码将开源。