Detecting Contradictory COVID-19 Drug Efficacy Claims from Biomedical Literature
This addresses the 'infodemic' of conflicting scientific claims during the COVID-19 pandemic, aiding domain experts in navigating complex literature, though it is incremental as it applies existing NLP methods to a new domain-specific dataset.
The paper tackles the problem of contradictory COVID-19 drug efficacy claims by framing it as a natural language inference task, resulting in models that help domain experts summarize and assess evidence for drugs like remdesivir and hydroxychloroquine.
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.