SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.08191 · 2020

RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering

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

In open-domain question answering, dense passage retrieval has become a new paradigm to retrieve relevant passages for finding answers. Typically, the dual-encoder architecture is adopted to learn dense representations of questions and passages for semantic matching. However, it is difficult to effectively train a dual-encoder due to the challenges including the discrepancy between training and inference, the existence of unlabeled positives and limited training data. To address these challenges, we propose an optimized training approach, called RocketQA, to improving dense passage retrieval. We make three major technical contributions in RocketQA, namely cross-batch negatives, denoised hard negatives and data augmentation. The experiment results show that RocketQA significantly outperforms previous state-of-the-art models on both MSMARCO and Natural Questions. We also conduct extensive experiments to examine the effectiveness of the three strategies in RocketQA. Besides, we demonstrate that the performance of end-to-end QA can be improved based on our RocketQA retriever.

For agents

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

get_harvested_code_for_paper("2010.08191")
get_code_for_paper("2010.08191")
have("2010.08191")

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

curl https://syntology.ai/api/ran/2010.08191.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.08191.svg)](https://syntology.ai/paper/2010.08191)

Connect an agent — have() is free.