Recently, dense passage retrieval has become a mainstream approach to finding
relevant information in various natural language processing tasks. A number of
studies have been devoted to improving the widely adopted dual-encoder
architecture. However, most of the previous studies only consider query-centric
similarity relation when learning the dual-encoder retriever. In order to
capture more comprehensive similarity relations, we propose a novel approach
that leverages both query-centric and PAssage-centric sImilarity Relations
(called PAIR) for dense passage retrieval. To implement our approach, we make
three major technical contributions by introducing formal formulations of the
two kinds of similarity relations, generating high-quality pseudo labeled data
via knowledge distillation, and designing an effective two-stage training
procedure that incorporates passage-centric similarity relation constraint.
Extensive experiments show that our approach significantly outperforms previous
state-of-the-art models on both MSMARCO and Natural Questions datasets.

该研究提出了一种利用查询中心和段落中心相似性关系（称为 PAIR）进行密集段落检索的新方法，同时引入了高质量的伪标记数据，通过两阶段训练过程，显著提高了检索性能。