Abstract
Over the past few decades, the amount of scientific articles and technicalliterature has increased exponentially in size. Consequently, there is a greatneed for systems that can ingest these documents at scale and make theircontent discoverable. Unfortunately, both the format of these documents (e.g.the PDF format or bitmap images) as well as the presentation of the data (e.g.complex tables) make the extraction of qualitative and quantitive dataextremely challenging. We present a platform to ingest documents at scale whichis powered by Machine Learning techniques and allows the user to train custommodels on document collections. We show precision/recall results greater than97% with regard to conversion to structured formats, as well as scalingevidence for each of the microservices constituting the platform.