SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.06027 · ACL Findings · 2021

PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval

Jing Liu, Ji-Rong Wen, Wayne Zhao, Qiaoqiao She, Hua Wu, Ruiyang Ren, Haifeng Wang, Shangwen Lv, Yingqi Qu

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 1 .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2108.06027")
get_code_for_paper("2108.06027")
have("2108.06027")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2108.06027.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2108.06027.svg)](https://syntology.ai/paper/2108.06027)

Connect an agent — have() is free.