Year: 2020
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Xiong, Wenhan, Li, Xiang Lorraine, Iyer, Srini, Du, Jingfei, Lewis, Patrick, Wang, William Yang, Mehdad, Yashar, Yih, Wen-tau, Riedel, Sebastian, Kiela, Douwe, Oğuz, Barlas
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3088148579