Content: B1: Automatic Generation of Description Logic-based Biomedical Ontologies

B1: Automatic Generation of Description Logic-based Biomedical Ontologies

Ontologies such as the Gene Ontology and SNOMED CT play a major role in biology and medicine since they facilitate data integration and the consistent exchange of information between different entities. They can also be used to index and annotate data and literature, thus enabling efficient search and analysis. Unfortunately, creating the required ontologies manually is a complex, error-prone, and time and personnel-consuming effort. For this reason, approaches that try to learn ontologies automatically from text and data have been developed. The ontologies generated by these approaches are, however, usually not formal ontologies, i.e., the concepts learned by these approaches are not equipped with a formal definition. The goal of this project is to combine the expertise in ontology learning from text of Prof. Schroeder’s group with the Description Logic expertise of Prof. Baader’s group in order to develop approaches for learning Description Logic-based ontologies from text and data. The main idea is to apply non-standard Description Logic inferences developed in Prof. Baader’s group to the result of the ontology learning approach developed in Prof. Schroeder’s group in order to generate concept definitions and additional constraints (general concept inclusions). The envisioned approach is hybrid since the non-standard inferences will be modified such that they can take into account numerical information on the quality of the results produced by the ontology learning approaches.

Milestone Video May 2014

Missing flash plugin. Please download the latest Adobe Flash Player:
Get Adobe Flash Player