Hybrid and Collaborative Passage Reranking

Zongmeng Zhang, Wengang Zhou, Jiaxin Shi, Houqiang Li


Abstract
In passage retrieval system, the initial passage retrieval results may be unsatisfactory, which can be refined by a reranking scheme. Existing solutions to passage reranking focus on enriching the interaction between query and each passage separately, neglecting the context among the top-ranked passages in the initial retrieval list. To tackle this problem, we propose a Hybrid and Collaborative Passage Reranking (HybRank) method, which leverages the substantial similarity measurements of upstream retrievers for passage collaboration and incorporates the lexical and semantic properties of sparse and dense retrievers for reranking. Besides, built on off-the-shelf retriever features, HybRank is a plug-in reranker capable of enhancing arbitrary passage lists including previously reranked ones. Extensive experiments demonstrate the stable improvements of performance over prevalent retrieval and reranking methods, and verify the effectiveness of the core components of HybRank.
Anthology ID:
2023.findings-acl.880
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14003–14021
Language:
URL:
https://aclanthology.org/2023.findings-acl.880
DOI:
10.18653/v1/2023.findings-acl.880
Bibkey:
Cite (ACL):
Zongmeng Zhang, Wengang Zhou, Jiaxin Shi, and Houqiang Li. 2023. Hybrid and Collaborative Passage Reranking. In Findings of the Association for Computational Linguistics: ACL 2023, pages 14003–14021, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Hybrid and Collaborative Passage Reranking (Zhang et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.880.pdf
Video:
 https://aclanthology.org/2023.findings-acl.880.mp4