Efficient Passage Retrieval with Hashing for Open-domain Question Answering

Ikuya Yamada, Akari Asai, Hannaneh Hajishirzi


Abstract
Most state-of-the-art open-domain question answering systems use a neural retrieval model to encode passages into continuous vectors and extract them from a knowledge source. However, such retrieval models often require large memory to run because of the massive size of their passage index. In this paper, we introduce Binary Passage Retriever (BPR), a memory-efficient neural retrieval model that integrates a learning-to-hash technique into the state-of-the-art Dense Passage Retriever (DPR) to represent the passage index using compact binary codes rather than continuous vectors. BPR is trained with a multi-task objective over two tasks: efficient candidate generation based on binary codes and accurate reranking based on continuous vectors. Compared with DPR, BPR substantially reduces the memory cost from 65GB to 2GB without a loss of accuracy on two standard open-domain question answering benchmarks: Natural Questions and TriviaQA. Our code and trained models are available at https://github.com/studio-ousia/bpr.
Anthology ID:
2021.acl-short.123
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
979–986
Language:
URL:
https://aclanthology.org/2021.acl-short.123
DOI:
10.18653/v1/2021.acl-short.123
Bibkey:
Cite (ACL):
Ikuya Yamada, Akari Asai, and Hannaneh Hajishirzi. 2021. Efficient Passage Retrieval with Hashing for Open-domain Question Answering. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 979–986, Online. Association for Computational Linguistics.
Cite (Informal):
Efficient Passage Retrieval with Hashing for Open-domain Question Answering (Yamada et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-short.123.pdf
Video:
 https://aclanthology.org/2021.acl-short.123.mp4
Code
 studio-ousia/bpr
Data
Natural QuestionsTQATriviaQA