On Complementarity Objectives for Hybrid Retrieval
Dohyeon Lee, Seung-won Hwang, Kyungjae Lee, Seungtaek Choi, Sunghyun Park
Abstract
Dense retrieval has shown promising results in various information retrieval tasks, and hybrid retrieval, combined with the strength of sparse retrieval, has also been actively studied. A key challenge in hybrid retrieval is to make sparse and dense complementary to each other. Existing models have focused on dense models to capture “residual” features neglected in the sparse models. Our key distinction is to show how this notion of residual complementarity is limited, and propose a new objective, denoted as RoC (Ratio of Complementarity), which captures a fuller notion of complementarity. We propose a two-level orthogonality designed to improve RoC, then show that the improved RoC of our model, in turn, improves the performance of hybrid retrieval. Our method outperforms all state-of-the-art methods on three representative IR benchmarks: MSMARCO-Passage, Natural Questions, and TREC Robust04, with statistical significance. Our finding is also consistent in various adversarial settings.- Anthology ID:
- 2023.acl-long.746
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 13357–13368
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.746
- DOI:
- 10.18653/v1/2023.acl-long.746
- Cite (ACL):
- Dohyeon Lee, Seung-won Hwang, Kyungjae Lee, Seungtaek Choi, and Sunghyun Park. 2023. On Complementarity Objectives for Hybrid Retrieval. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13357–13368, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- On Complementarity Objectives for Hybrid Retrieval (Lee et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.acl-long.746.pdf