Keywords: multi-hop question answering, recursive dense retrieval, open domain complex question answering
Abstract: 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.
One-sentence Summary: We propose a simple yet effective multi-hop dense retrieval approach for answering complex open-domain questions.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Code: [![github](/images/github_icon.svg) facebookresearch/multihop_dense_retrieval](https://github.com/facebookresearch/multihop_dense_retrieval)
Data: [HotpotQA](https://paperswithcode.com/dataset/hotpotqa), [Natural Questions](https://paperswithcode.com/dataset/natural-questions)