With so much information stored in textual documents and resources, it is necessary to improve the way in which users query and extract useful information from them. To that end, KSE Lab is investigating knowledge-based approaches for Natural Language Processing and Understanding that make use of general and domain specific data sources, knowledge-bases, and ontologies (including knowledge of their structures) to extract knowledge from text, formalise it, and link it to that which is already known.
Applications of this work range from generating formal models of Software (or Business) Requirements Specifications written in controlled English, to information extraction on unrestricted text. Such work is strongly related to our expertise in Advanced Knowledge Technologies, including the use of ontologies, configuration, and the integration of information sources and ontologies.
- Formal Models from Controlled Natural Language via Cognitive Grammar and Configuration
- DSTO Doctrine to Code Project