Automatically generating question-answer pairs for assessing basic reading comprehension in Swedish

This work addresses the need for automated assessment tools in education, specifically for reading comprehension in Swedish, though it is incremental as it applies an existing method to a new language.

The paper tackled the problem of automatically generating reading comprehension questions from Swedish text using the Quinductor method, finding it to be a viable approach that can serve as a strong baseline for neural-network-based methods.