Vice President of Data Science
Director of Data Science
Senior Machine Learning Scientist
Since the COVID-19 pandemic broke out, the academic and scientific research community, as well as industry and governments around the world have joined forces in an unprecedented manner to fight the threat and discover efficient treatments as well as vaccine solutions to prevent further spread of the virus and its multiple mutations. The key for these advancements has been the timely, accurate, peer-reviewed, and efficiently communicated information of any novel research findings. In parallel, there have been several technical challenges, one of the most important being the development of tools and methods that can facilitate the efficient filtering of relevant information, as well as the ability to extract the latest and most reliable insights for the virus from the COVID-19 scientific literature.
This talk will present two technologies that have been developed based on state-of-the-art methods of machine learning and natural language processing that support the efficient retrieval and filtering of the core COVID-19 literature and the ability to query it using questions formulated in natural language. From the development of these two technologies, we can report on the significance and value of active learning as a mechanism to mitigate the risks of content and vocabulary drift of the literature, as well as on the importance of employing learning to rank methodologies for the efficient retrieval of information from the scientific articles.