Answering Questions on COVID-19 in Real-Time
This work addresses the knowledge gap for researchers combating COVID-19 and future pandemics, though it is incremental as it applies existing QA and IR methods to a new domain.
The authors tackled the lack of accessible information during the COVID-19 pandemic by developing covidAsk, a real-time question answering system that combines biomedical text mining and QA techniques, evaluated on a manually created dataset from sources like CDC and WHO.
The recent outbreak of the novel coronavirus is wreaking havoc on the world and researchers are struggling to effectively combat it. One reason why the fight is difficult is due to the lack of information and knowledge. In this work, we outline our effort to contribute to shrinking this knowledge vacuum by creating covidAsk, a question answering (QA) system that combines biomedical text mining and QA techniques to provide answers to questions in real-time. Our system also leverages information retrieval (IR) approaches to provide entity-level answers that are complementary to QA models. Evaluation of covidAsk is carried out by using a manually created dataset called COVID-19 Questions which is based on information from various sources, including the CDC and the WHO. We hope our system will be able to aid researchers in their search for knowledge and information not only for COVID-19, but for future pandemics as well.