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

RocketQA: оптимизированный подход к обучению для плотного извлечения фрагментов текста в системах ответов на вопросы в открытом домене
Wayne Xin Zhao, Haifeng Wang, Hua Wu, Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Daxiang Dong
2021-01-01
SCID:  54.1/ap45h9ck Discuss with AI
RocketQAdense passage retrievalopen-domain question answeringoptimized training
Abstract (AI)
Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Wayne Xin Zhao, Daxiang Dong, Hua Wu, Haifeng Wang. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.
Key Findings
1
No specific empirical findings, quantitative improvements, or methodological claims can be reliably extracted from the supplied text.
2
The provided text includes bibliographic information and a title but no abstract content describing methods, experiments, results, or limitations.
Research Object

dense passage retrieval for open-domain question answering

Research Subject

optimized training approach for improving retrieval effectiveness

Publication Details
Publication Date
2021-01-01
Journal
Publisher
ISSN
Cited by
352
Access Type
Author Information
Authors
Wayne Xin Zhao
Haifeng Wang
Hua Wu
Yingqi Qu
Yuchen Ding
Jing Liu
Kai Liu
Ruiyang Ren
Daxiang Dong
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%