Contextual Query Expansion Model for Conducting COVID-19 Scholarly Search

With the onset of the Coronavirus Disease 2019 (COVID-19) pandemic, there has been a surge in the number of publicly available biomedical information sources, which makes it an increasingly challenging research goal to retrieve a relevant text to a topic of interest. In this research work, we propose a Contextual Query Expansion Model based on clinical Domain knowledge (CQED), for formalizing an effective search over PubMed to retrieve relevant COVID-19 scholarly articles to a given information need. The proposed model utilizes both contextual and biomedical domain-specific information to expand queries posed to PubMed. The Model includes a multi-head attention mechanism that is trained alongside a learning-to-rank model for re-ranking the list of generated expansion candidate terms. The Model can have four different variations, depending upon the learning path adopted for training and re-ranking the candidate expansion terms. Our results depict that the proposed model successfully outperforms all existing state-of-the-art baselines.