Searching Scientific Literature for Answers on COVID-19 Questions
This work addresses the problem of information retrieval during a pandemic for scientists, clinicians, and policymakers, but it appears incremental as it builds on existing ranking algorithms and a specific challenge.
The paper tackles the challenge of retrieving reliable answers from scientific literature for COVID-19 questions, proposing a novel neural retrieval method and demonstrating its effectiveness on the TREC COVID search track.
Finding answers related to a pandemic of a novel disease raises new challenges for information seeking and retrieval, as the new information becomes available gradually. TREC COVID search track aims to assist in creating search tools to aid scientists, clinicians, policy makers and others with similar information needs in finding reliable answers from the scientific literature. We experiment with different ranking algorithms as part of our participation in this challenge. We propose a novel method for neural retrieval, and demonstrate its effectiveness on the TREC COVID search.