Common document ranking pipelines in search systems are cascade systems that involve multiple ranking layers to integrate different information step-by-step. In this paper, we propose a novel re-ranker Fusion-in-T5 (FiT5), which integrates text matching information, ranking features, and global document information into one single unified model via templated-based input and global attention. Experiments on passage ranking benchmarks MS MARCO and TREC DL show that FiT5, as one single model, significantly improves ranking performance over complex cascade pipelines. Analysis finds that through attention fusion, FiT5 jointly utilizes various forms of ranking information via gradually attending to related documents and ranking features, and improves the detection of subtle nuances. Our code is open-sourced at https://github.com/OpenMatch/FiT5.
@article{arxiv.2305.14685,
title = {Fusion-in-T5: Unifying Document Ranking Signals for Improved Information Retrieval},
author = {Shi Yu and Chenghao Fan and Chenyan Xiong and David Jin and Zhiyuan Liu and Zhenghao Liu},
journal= {arXiv preprint arXiv:2305.14685},
year = {2024}
}