AI for Representation and Reasoning in Knowledge Bases of Science | Andrew McCallum
Inaugural AI Research Week, hosted by the MIT-IBM Watson AI Lab. Andrew McCallum discusses the knowledge graph of scientific entities, including genes, proteins, symptoms, diseases, drugs, etc and the relations among them. Andrew describes advances in machine learning and deep neural networks for extracting entity-relations from the natural language full text of millions of scientific papers, as well as for representing and reasoning about the resulting knowledge base. Andrew introduces "universal schema," an approach that embeds many database schema and natural language expressions into a common semantic vector space, and describes applications of this work to building scientific knowledge bases, including biomedicine and material science.
Keynote Speaker
Andrew McCallum, Distinguished Professor of Computer Science, UMass Amherst
Introduction by Lisa Amini, Lab Director, IBM Research Cambridge