Information retrieval systems implemented from CORD-19: key tools in managing information about the COVID-19

Abstract

Research on the coronavirus has generated an extraordinary production of scientific documents. Their treatment and assimilation by the scientific community has required the help of specifically designed information retrieval systems. Some of the world's leading institutions involved in the fight against the pandemic have developed the CORD-19 dataset that stands out from other projects of a similar nature. The documents collected in this source have been processed by various information retrieval tools, sometimes prototypes or previously implemented systems. The typology and main characteristics of these systems have been analysed, concluding that there are three main non-exclusive categories among them: terminological search, information visualisation and natural language processing. It should be noted that most of them use semantic search technologies in order to facilitate the acquisition of knowledge by researchers and to help them in their enormous task. The crisis caused by the pandemic has been taken advantage of by semantic search engines to find their site.