Passage-based BM25 Hard Negatives: A Simple and Effective Negative Sampling Strategy For Dense Retrieval

Thanh-Do Nguyen, Chi Minh Bui, Thi-Hai-Yen Vuong, Xuan-Hieu Phan


Anthology ID:
2023.paclic-1.59
Volume:
Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation
Month:
December
Year:
2023
Address:
Hong Kong, China
Editors:
Chu-Ren Huang, Yasunari Harada, Jong-Bok Kim, Si Chen, Yu-Yin Hsu, Emmanuele Chersoni, Pranav A, Winnie Huiheng Zeng, Bo Peng, Yuxi Li, Junlin Li
Venue:
PACLIC
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
591–599
Language:
URL:
https://aclanthology.org/2023.paclic-1.59
DOI:
Bibkey:
Cite (ACL):
Thanh-Do Nguyen, Chi Minh Bui, Thi-Hai-Yen Vuong, and Xuan-Hieu Phan. 2023. Passage-based BM25 Hard Negatives: A Simple and Effective Negative Sampling Strategy For Dense Retrieval. In Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation, pages 591–599, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Passage-based BM25 Hard Negatives: A Simple and Effective Negative Sampling Strategy For Dense Retrieval (Nguyen et al., PACLIC 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2023.paclic-1.59.pdf