{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/rocketqa-an-optimized-training-approach-to","title":"RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering","arxiv_id":"2010.08191","date":"2020-10-16","proceeding":"NAACL 2021 4","authors":["Yingqi Qu","Yuchen Ding","Jing Liu","Kai Liu","Ruiyang Ren","Wayne Xin Zhao","daxiang dong","Hua Wu","Haifeng Wang"],"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.","url_abs":"https://arxiv.org/abs/2010.08191v2","url_pdf":"https://arxiv.org/pdf/2010.08191v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"rocketqa-an-optimized-training-approach-to","repo_url":"https://github.com/paddlepaddle/rocketqa","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"natural-questions","task_name":"Natural Questions"},{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"passage-retrieval","task_name":"Passage Retrieval"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/passage-retrieval-on-natural-questions","task":"Passage Retrieval","dataset":"Natural Questions","model":"RocketQA","rank_in_archive_order":4,"of":10,"metrics":{"Precision@100":"88.5","Precision@20":"82.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.08191","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}