Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval

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.

PDF Abstract ICLR 2021 PDF ICLR 2021 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Question Answering HotpotQA Recursive Dense Retriever ANS-EM 0.623 # 14
ANS-F1 0.753 # 16
SUP-EM 0.575 # 4
SUP-F1 0.809 # 14
JOINT-EM 0.418 # 9
JOINT-F1 0.666 # 14

Methods


No methods listed for this paper. Add relevant methods here