Two-Step Question Retrieval for Open-Domain QA
Yeon Seonwoo, Juhee Son, Jiho Jin, Sang-Woo Lee, Ji-Hoon Kim, Jung-Woo Ha, Alice Oh
Abstract
The retriever-reader pipeline has shown promising performance in open-domain QA but suffers from a very slow inference speed. Recently proposed question retrieval models tackle this problem by indexing question-answer pairs and searching for similar questions. These models have shown a significant increase in inference speed, but at the cost of lower QA performance compared to the retriever-reader models. This paper proposes a two-step question retrieval model, SQuID (Sequential Question-Indexed Dense retrieval) and distant supervision for training. SQuID uses two bi-encoders for question retrieval. The first-step retriever selects top-k similar questions, and the second-step retriever finds the most similar question from the top-k questions. We evaluate the performance and the computational efficiency of SQuID. The results show that SQuID significantly increases the performance of existing question retrieval models with a negligible loss on inference speed.- Anthology ID:
- 2022.findings-acl.117
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2022
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1487–1492
- Language:
- URL:
- https://aclanthology.org/2022.findings-acl.117
- DOI:
- 10.18653/v1/2022.findings-acl.117
- Cite (ACL):
- Yeon Seonwoo, Juhee Son, Jiho Jin, Sang-Woo Lee, Ji-Hoon Kim, Jung-Woo Ha, and Alice Oh. 2022. Two-Step Question Retrieval for Open-Domain QA. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1487–1492, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Two-Step Question Retrieval for Open-Domain QA (Seonwoo et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2022.findings-acl.117.pdf
- Code
- yeonsw/squid
- Data
- Natural Questions, PAQ, TriviaQA