👋 Andrei Cătălin Coman
Machine reading extracts valuable knowledge from text (e.g. in the form of entities and their relationships) and stores it in a knowledge base or knowledge graph for further use. We approach this task as a continual learning problem, using the current knowledge base to learn how to extract information from text, and using the text to extract new knowledge to add to the knowledge base. In this project, we develop deep learning approaches to this task which induce a joint representation of both the text and the knowledge base.