Nothing Special   »   [go: up one dir, main page]

RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking

Ruiyang Ren, Yingqi Qu, Jing Liu, Wayne Xin Zhao, QiaoQiao She, Hua Wu, Haifeng Wang, Ji-Rong Wen


Abstract
In various natural language processing tasks, passage retrieval and passage re-ranking are two key procedures in finding and ranking relevant information. Since both the two procedures contribute to the final performance, it is important to jointly optimize them in order to achieve mutual improvement. In this paper, we propose a novel joint training approach for dense passage retrieval and passage reranking. A major contribution is that we introduce the dynamic listwise distillation, where we design a unified listwise training approach for both the retriever and the re-ranker. During the dynamic distillation, the retriever and the re-ranker can be adaptively improved according to each other’s relevance information. We also propose a hybrid data augmentation strategy to construct diverse training instances for listwise training approach. Extensive experiments show the effectiveness of our approach on both MSMARCO and Natural Questions datasets. Our code is available at https://github.com/PaddlePaddle/RocketQA.
Anthology ID:
2021.emnlp-main.224
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2825–2835
Language:
URL:
https://aclanthology.org/2021.emnlp-main.224
DOI:
10.18653/v1/2021.emnlp-main.224
Bibkey:
Cite (ACL):
Ruiyang Ren, Yingqi Qu, Jing Liu, Wayne Xin Zhao, QiaoQiao She, Hua Wu, Haifeng Wang, and Ji-Rong Wen. 2021. RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2825–2835, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking (Ren et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.224.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.224.mp4
Code
 paddlepaddle/rocketqa
Data
MS MARCONatural Questions