Joint Inference of Retrieval and Generation for Passage Re-ranking

Wei Fang, Yung-Sung Chuang, James Glass


Abstract
Passage retrieval is a crucial component of modern open-domain question answering (QA) systems, providing information for downstream QA components to generate accurate and transparent answers. In this study we focus on passage re-ranking, proposing a simple yet effective method, Joint Passage Re-ranking (JPR), that optimizes the mutual information between query and passage distributions, integrating both cross-encoders and generative models in the re-ranking process. Experimental results demonstrate that JPR outperforms conventional re-rankers and language model scorers in both open-domain QA retrieval settings and diverse retrieval benchmarks under zero-shot settings.
Anthology ID:
2024.findings-eacl.151
Volume:
Findings of the Association for Computational Linguistics: EACL 2024
Month:
March
Year:
2024
Address:
St. Julian’s, Malta
Editors:
Yvette Graham, Matthew Purver
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2289–2298
Language:
URL:
https://aclanthology.org/2024.findings-eacl.151
DOI:
Bibkey:
Cite (ACL):
Wei Fang, Yung-Sung Chuang, and James Glass. 2024. Joint Inference of Retrieval and Generation for Passage Re-ranking. In Findings of the Association for Computational Linguistics: EACL 2024, pages 2289–2298, St. Julian’s, Malta. Association for Computational Linguistics.
Cite (Informal):
Joint Inference of Retrieval and Generation for Passage Re-ranking (Fang et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.findings-eacl.151.pdf
Software:
 2024.findings-eacl.151.software.zip
Video:
 https://preview.aclanthology.org/nschneid-patch-4/2024.findings-eacl.151.mp4