Propositional and Non-at-issue Content in Text Generation: Exploring the QUD–Perspective

QUD, i.e. Question under discussion-based approaches to discourse structuring facilitate concise
analyses of a bunch of different pragmatic phenomena, ranging from the analysis of focus/background
structures to dialogue moves. Analyzing texts as sequences of answers to a structured range of implicit
or explicit questions underlines the inherent dialogical nature of text production and interpretation.
We investigate the descriptive and explanatory strength of the QUD-approach for the generation of texts (NLG).
The aims of this project are:

• Determining the appropriateness of QUD-based document planning, both from a computational
  and a theoretical perspective.
• Determining possible limitations of QUD-based document planning by incorporating evaluative content
  into the semantic input for text generation.
• Developing a method for analyzing texts (reports on vehicles) to achieve QUD structures for NLG.