Adapting Text Generation to Individual Users (A08*)

• Subject Area: Applied Linguistics, Computational Linguistics
• Term: since 2022
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 232722074

A8 is concerned with writing text that a specific reader can understand optimally. Different choices of linguistic encoding are optimal for different readers because they differ in their cognitive properties. We will investigate, from a psycholinguistic perspective, how cognitive properties can be diagnosed by eye-tracking the reader and what linguistic features are optimal given certain cognitive properties. From a computational perspective, we will develop text-to-text generation systems which use these psycholinguistic insights to rewrite text for optimal comprehension while the user is reading it.

• DFG Programme: Collaborative Research Centres
• Subproject of: SFB 1102: Information Density and Linguistic Encoding
• Applicant Institution: Universität des Saarlandes
• Project Heads: Professorin Dr. Vera Demberg; Professor Dr. Alexander Koller