Semantic Enrichment of Pretrained Embedding Output for Unsupervised IR

The rapid growth of scientific literature in the biomedical and clinical domain has significantly com-plicated the identification of information of interest by researchers as well as other practitioners. Moreimportantly, the rapid emergence of new topics and findings, often hinders the performance of super-vised approaches, due to the lack of relevant annotated data. The global COVID-19 pandemic furtherhighlighted the need to query and navigate uncharted ground in the scientific literature in a promptand efficient way.In this paper we investigate the potential of semantically enhancing deep transformer architecturesusing SNOMED-CT in order to answer user queries in an unsupervised manner. Our proposed systemattempts to filter and re-rank documents related to a query that were initially retrieved using BERTmodels. To achieve that, we enhance queries and documents with SNOMED-CT concepts and then im-pose filters on concept co-occurrence between them. We evaluate this approach on OHSUMED datasetand show competitive performance and we also present our approach for adapting such an approach tofull papers, such as kaggle’s CORD-19 full-text dataset challenge.