PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval
This work addresses the limitation of existing dense retrieval methods that only consider query-centric relations, offering a novel approach for improving information retrieval in natural language processing tasks.
The paper tackled the problem of dense passage retrieval by proposing PAIR, which leverages both query-centric and passage-centric similarity relations, resulting in significant performance improvements over previous state-of-the-art models on MSMARCO and Natural Questions datasets.
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.