BriefGPT.xyz
May, 2022
TREC 2021深度学习赛道上的PASH：多级排序的生成增强模型
PASH at TREC 2021 Deep Learning Track: Generative Enhanced Model for Multi-stage Ranking
HTML
PDF
Yixuan Qiao, Hao Chen, Yongquan Lai, Jun Wang, Tuozhen Liu...
TL;DR
本文介绍了PASH参加TREC 2021深度学习赛道所采用的稀疏和稠密检索方法，采用基于模型预训练的点对和成对排名策略，通过引入T5生成模型进一步提高了性能。
Abstract
This paper describes the
pash
participation in
trec 2021
deep learning
Track. In the recall stage, we adopt a scheme combining
→