Abstract
Given its effectiveness on knowledge-intensive natural language processing tasks, dense retrieval models have become increasingly popular. Specifically, the de-facto architecture for open-domain question answering uses two isomorphic encoders that are initialized from the same pretrained model but separately parameterized for questions and passages. This biencoder architecture is parameter-inefficient in that there is no parameter sharing between encoders. Further, recent studies show that such dense retrievers underperform BM25 in various settings. We thus propose a new architecture, Task-Aware Specialization for dEnse Retrieval (TASER), which enables parameter sharing by interleaving shared and specialized blocks in a single encoder. Our experiments on five question answering datasets show that TASER can achieve superior accuracy, surpassing BM25, while using about 60% of the parameters as bi-encoder dense retrievers. In out-of-domain evaluations, TASER is also empirically more robust than bi-encoder dense retrievers. Our code is available at https://github.com/microsoft/taser.- Anthology ID:
- 2023.acl-short.159
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short 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:
- 1864–1875
- Language:
- URL:
- https://aclanthology.org/2023.acl-short.159
- DOI:
- 10.18653/v1/2023.acl-short.159
- Cite (ACL):
- Hao Cheng, Hao Fang, Xiaodong Liu, and Jianfeng Gao. 2023. Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1864–1875, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering (Cheng et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/landing_page/2023.acl-short.159.pdf