Please use this identifier to cite or link to this item:
Title: Zero-shot Fact Verification by Claim Generation
Authors: Pan, L
Chen, W
Xiong, W
Kan, MY 
Wang, WY
Issue Date: 1-Jan-2021
Citation: Pan, L, Chen, W, Xiong, W, Kan, MY, Wang, WY (2021-01-01). Zero-shot Fact Verification by Claim Generation 2 : 476-483. ScholarBank@NUS Repository.
Abstract: Neural models for automated fact verification have achieved promising results thanks to the availability of large, human-annotated datasets. However, for each new domain that requires fact verification, creating a dataset by manually writing claims and linking them to their supporting evidence is expensive. We develop QACG, a framework for training a robust fact verification model by using automaticallygenerated claims that can be supported, refuted, or unverifiable from evidence from Wikipedia. QACG generates question-answer pairs from the evidence and then convert them into different types of claims. Experiments on the FEVER dataset show that our QACG framework significantly reduces the demand for human-annotated training data. In a zeroshot scenario, QACG improves a RoBERTa model's F1 from 50% to 77%, equivalent in performance to 2K+ manually-curated examples. Our QACG code is publicly available.
ISBN: 9781954085527
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
2105.14682.pdf777.89 kBAdobe PDF



Page view(s)

checked on Sep 22, 2022


checked on Sep 22, 2022

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.