TY - GEN

T1 - Generating Scientific Claims for Zero-Shot Scientific Fact Checking

AU - Wright, Dustin

AU - Wadden, David

AU - Lo, Kyle

AU - Kuehl, Bailey

AU - Cohan, Arman

AU - Augenstein, Isabelle

AU - Wang, Lucy Lu

PY - 2022

Y1 - 2022

N2 - Automated scientific fact checking is difficult due to the complexity of scientific language and a lack of significant amounts of training data, as annotation requires domain expertise. To address this challenge, we propose scientific claim generation, the task of generating one or more atomic and verifiable claims from scientific sentences, and demonstrate its usefulness in zero-shot fact checking for biomedical claims. We propose CLAIMGEN-BART, a new supervised method for generating claims supported by the literature, as well as KBIN, a novel method for generating claim negations. Additionally, we adapt an existing unsupervised entity-centric method of claim generation to biomedical claims, which we call CLAIMGEN-ENTITY. Experiments on zero-shot fact checking demonstrate that both CLAIMGEN-ENTITY and CLAIMGEN-BART, coupled with KBIN, achieve up to 90% performance of fully supervised models trained on manually annotated claims and evidence. A rigorous evaluation study demonstrates significant improvement in generated claim and negation quality over existing baselines

AB - Automated scientific fact checking is difficult due to the complexity of scientific language and a lack of significant amounts of training data, as annotation requires domain expertise. To address this challenge, we propose scientific claim generation, the task of generating one or more atomic and verifiable claims from scientific sentences, and demonstrate its usefulness in zero-shot fact checking for biomedical claims. We propose CLAIMGEN-BART, a new supervised method for generating claims supported by the literature, as well as KBIN, a novel method for generating claim negations. Additionally, we adapt an existing unsupervised entity-centric method of claim generation to biomedical claims, which we call CLAIMGEN-ENTITY. Experiments on zero-shot fact checking demonstrate that both CLAIMGEN-ENTITY and CLAIMGEN-BART, coupled with KBIN, achieve up to 90% performance of fully supervised models trained on manually annotated claims and evidence. A rigorous evaluation study demonstrates significant improvement in generated claim and negation quality over existing baselines

U2 - 10.18653/v1/2022.acl-long.175

DO - 10.18653/v1/2022.acl-long.175

M3 - Article in proceedings

BT - Generating Scientific Claims for Zero-Shot Scientific Fact Checking

PB - Association for Computational Linguistics

T2 - 60th Annual Meeting of the Association for Computational Linguistics

Y2 - 23 May 2022 through 25 May 2022

ER -