The knowledge contained in digital lectures and articles used in eLearning platforms like Moodle and Blackboard, is creating new demands for intelligent retrieval mechanisms. One basic approach in support of such retrieval mechanisms is the generation of semantic annotation, based on ontologies describing both the field and the structure of the texts themselves. Many current approaches use statistical methods similar to the ones employed by Google to find correlations within the texts. While successful and efficient, this approach fails to take advantage of the additional information provided by the structure of the sources, or, i.e. the upper ontology used by the author. mArachna is based on natural language processing techniques, taking advantage of characteristic linguistic structures defined by the language used in mathematical texts. It creates a knowledge base from the mathematical relations presented in a text, mapping the ontology onto the structure of the knowledge base.