Prioritization of COVID-19-related literature via unsupervised keyphrase extraction and document representation learning
This provides a tool for researchers to navigate the overwhelming volume of COVID-19-related scientific papers, though it is incremental as it builds on existing embedding and keyphrase extraction methods.
The paper tackled the problem of efficiently exploring the vast COVID-19 literature by developing a system that uses unsupervised keyphrase extraction and document representation learning to annotate and prioritize papers, demonstrated through case studies in medicinal chemistry.
The COVID-19 pandemic triggered a wave of novel scientific literature that is impossible to inspect and study in a reasonable time frame manually. Current machine learning methods offer to project such body of literature into the vector space, where similar documents are located close to each other, offering an insightful exploration of scientific papers and other knowledge sources associated with COVID-19. However, to start searching, such texts need to be appropriately annotated, which is seldom the case due to the lack of human resources. In our system, the current body of COVID-19-related literature is annotated using unsupervised keyphrase extraction, facilitating the initial queries to the latent space containing the learned document embeddings (low-dimensional representations). The solution is accessible through a web server capable of interactive search, term ranking, and exploration of potentially interesting literature. We demonstrate the usefulness of the approach via case studies from the medicinal chemistry domain.