Joint Passage Ranking for Diverse Multi-Answer Retrieval
Sewon Min, Kenton Lee, Ming-Wei Chang, Kristina Toutanova, Hannaneh Hajishirzi
Abstract
We study multi-answer retrieval, an under-explored problem that requires retrieving passages to cover multiple distinct answers for a given question. This task requires joint modeling of retrieved passages, as models should not repeatedly retrieve passages containing the same answer at the cost of missing a different valid answer. Prior work focusing on single-answer retrieval is limited as it cannot reason about the set of passages jointly. In this paper, we introduce JPR, a joint passage retrieval model focusing on reranking. To model the joint probability of the retrieved passages, JPR makes use of an autoregressive reranker that selects a sequence of passages, equipped with novel training and decoding algorithms. Compared to prior approaches, JPR achieves significantly better answer coverage on three multi-answer datasets. When combined with downstream question answering, the improved retrieval enables larger answer generation models since they need to consider fewer passages, establishing a new state-of-the-art.- Anthology ID:
- 2021.emnlp-main.560
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6997–7008
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.560
- DOI:
- 10.18653/v1/2021.emnlp-main.560
- Cite (ACL):
- Sewon Min, Kenton Lee, Ming-Wei Chang, Kristina Toutanova, and Hannaneh Hajishirzi. 2021. Joint Passage Ranking for Diverse Multi-Answer Retrieval. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6997–7008, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Joint Passage Ranking for Diverse Multi-Answer Retrieval (Min et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2021.emnlp-main.560.pdf
- Data
- Natural Questions