Dutch Automated Writing evaluation through NLP

Start date
Sept. 15, 2022
End date
Sept. 14, 2023

About DAWN

The primary research objective of this project is to use machine learning techniques to enable automatic writing evaluation. Various innovative methods will be researched to detect and provide feedback on writing errors through different modules. Starting from sentence-level errors such as spelling and certain grammatical errors, and moving up to paragraph or even text-level errors that impact a text's coherence and therefore its readability. The research will also explore how to best provide feedback on writing products to motivate people and help them improve their writing skills in the process. For this, experiments on the use of generative language models will be included as well.