Detecting contradictory COVID-19 drug efficacy claims from biomedical literature.

Sosa, Daniel; Suresh, Malavika; Potts, Christopher; Altman, Russ

Abstract

The COVID-19 pandemic created a deluge of questionable and contradictory scientific claims about drug efficacy – an "infodemic" with lasting consequences for science and society. In this work, we argue that NLP models can help domain experts distill and understand the literature in this complex, high-stakes area. Our task is to automatically identify contradictory claims about COVID-19 drug efficacy. We frame this as a natural language inference problem and offer a new NLI dataset created by domain experts. The NLI framing allows us to create curricula combining existing datasets and our own. The resulting models are useful investigative tools. We provide a case study of how these models help a domain expert summarize and assess evidence concerning remdisivir and hydroxychloroquine.

Citation

SOSA, D.N., SURESH, M., POTTS, C. and ALTMAN, R.B. 2023. Detecting contradictory COVID-19 drug efficacy claims from biomedical literature. In Rogers, A., Boyd-Graber, J. and Okazaki, N. (eds.) Proceedings of the 61st Association for Computational Linguistics annual meeting 2023 (ACL 2023), 9-14 July 2023, Toronto, Candada. Stroudsburg, PA: ACL [online], volume 2: short papers, pages 694-713. Available from: https://doi.org/10.18653/v1/2023.acl-short.61

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 61st Association for Computational Linguistics annual meeting 2023 (ACL 2023)
• Start Date: Jul 9, 2023
• End Date: Jul 14, 2023
• Acceptance Date: Jun 9, 2023
• Online Publication Date: Sep 30, 2023
• Publication Date: Sep 30, 2023
• Deposit Date: Oct 5, 2023
• Publicly Available Date: Oct 5, 2023
• Publisher: ACL Association for Computational Linguistics
• Peer Reviewed: Peer Reviewed
• Volume: 2
• Pages: 694-713
• Book Title: Proceedings of the 61st Association for Computational Linguistics annual meeting 2023 (ACL 2023)
• ISBN: 9781959429715
• DOI: https://doi.org/10.18653/v1/2023.acl-short.61
• Keywords: COVID-19 panademic; Drug efficacy
• Public URL: https://rgu-repository.worktribe.com/output/2098528