Joint Research Project "Cultural Techniques and Their Mediatization"
Project A3: "Knowledge Ordering in Texts – Text Structuring and Structure Visualisation as Sources of Natural Ontologies"
Principal Investigator: Prof. Dr. Henning Lobin
Research Associate: Jana Klawitter
PhD Scholarship Holder: Mariana Hebborn
Research Assistant: Bastian Entrup
Knowledge in textual form is always presented as visually and hierarchically structured units of text, which is particularly true in the case of academic texts. The textual structure of academic texts effectively mirrors essential parts of the knowledge structure that is built up in the text. Knowledge structures have recently been formalized as ontologies and are used in the computational processing of knowledge.
At the same time, the linguistic and domain-specific conventions of the text type and of document design influence the text structure. The structuring of a modern dissertation thesis, for instance, represents a compromise between requirements of the text type and the methodological and conceptual structure of its subject-matter. On the other hand, in a presentation, the content of a complete talk is represented on the slides mostly as structure (using headings, bullet point lists, indentations etc.)
The project examines how visual-hierarchical structuring systems are constructed, how knowledge structures are encoded in them, and how they can be exploited to automatically derive ontological knowledge for navigation, archiving, or search tasks. The analyses are based on annotated corpora which are evaluated using statistical and rule-based methods. As a practical application, a prototype system for the automatic analysis of the textual outline of academic texts will be developed.
Compilation of a corpus of structured texts and design of an annotation system
Theoretical analysis of structuring systems as complex textual constructions
Linguistic analysis of structuring units with respect to lexical, syntactic, semantic and text-functional features
System design and implementation of a research prototype