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

276Citations
Citations of this article
260Readers
Mendeley users who have this article in their library.

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.

Cite

CITATION STYLE

APA

Qu, Y., Ding, Y., Liu, J., Liu, K., Ren, R., Zhao, W. X., … Wang, H. (2021). RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering. In NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference (pp. 5835–5847). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.naacl-main.466

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free