Wenhan Xiong, Xiang Lorraine Li, Srini Iyer, Jingfei Du, Patrick Lewis, William Yang Wang, Yashar Mehdad, Wen-tau Yih, Sebastian Riedel, Douwe Kiela, Barlas Oğuz
We propose a simple and efficient multi-hop dense retrieval approach for answering complex open-domain questions, which achieves state-of-the-art performance on two multi-hop datasets, HotpotQA and multi-evidence FEVER. Contrary to previous work, our method does not require access to any corpus-specific information, such as inter-document hyperlinks or human-annotated entity markers, and can be applied to any unstructured text corpus. Our system also yields a much better efficiency-accuracy trade-off, matching the best published accuracy on HotpotQA while being 10 times faster at inference time.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Question Answering | HotpotQA | ANS-EM | 0.623 | Recursive Dense Retriever |
| Question Answering | HotpotQA | ANS-F1 | 0.753 | Recursive Dense Retriever |
| Question Answering | HotpotQA | JOINT-EM | 0.418 | Recursive Dense Retriever |
| Question Answering | HotpotQA | JOINT-F1 | 0.666 | Recursive Dense Retriever |
| Question Answering | HotpotQA | SUP-EM | 0.575 | Recursive Dense Retriever |
| Question Answering | HotpotQA | SUP-F1 | 0.809 | Recursive Dense Retriever |