The Semantic Knowledge Representation (SKR) project develops programs that extract usable semantic information from biomedical text by building on the UMLS Knowledge Sources and the SPECIALIST NLP Tools. SKR resources are being applied in a variety of research initiatives aimed at identifying specific biomedical information in text. Programs under development include:

MetaMap	Maps noun phrases in free text to concepts in the UMLS Metathesaurus
MMTx	A Java-based, multi-platform version of MetaMap
SemRep	Uses the Semantic Network to determine relationships asserted between concepts in clinically-oriented text
SemGen	Identifies information about the genetic basis of disease
Arbiter	Extracts assertions about macromolecular binding relationships
EDGAR	Extracts information about the interaction of drugs and genes in the molecular pharmacology research literature