Methods and apparatus to facilitate annotation projects to extract structured information from free-form text using NLP techniques. Annotators explore text documents via automated preannotation functions, flexibly formulate annotation schemes and guidelines, annotate text, and adjust annotation labels, schemes and guidelines in real-time as a project evolves. NLP models are readily trained on iterative annotations of sample documents by domain experts in an active learning workflow. Trained models are then employed to automatically annotate a larger body of documents in a project dataset. Experts in a variety of domains can readily develop an annotation project for a specific use-case or business question. In one example, documents relating to the health care domain are effectively annotated and employed to train sophisticated NLP models that provide valuable insights regarding many facets of health care. In another example, annotation methods are enhanced by utilizing domain-specific information derived from a novel knowledge graph architecture.