Description

Apache cTAKES is a natural language-based clinical text analysis and knowledge extraction platform designed for healthcare sectors. It enables users to manage codable entities, temporal events, properties and relations, create a dictionary from NLM UMLS, execute raw data and view NLP metadata, view extracted UMLS and temporal information, design linguistic and semantic annotations, as well as determine entity attributes for the text span, the ontology mapping code and subject. Features include sentence boundary detection, rule-based tokenization, morphologic normalization, POS tagging capability, shallow parsing, named entity recognization, coreference resolver capability, and smoking status classification capability.