While exam-style questions are a fundamental educational tool serving a variety of
purposes, manual construction of questions is a complex process that requires training …

Question generation is an important yet challenging problem in Artificial Intelligence (AI),
which aims to generate natural and relevant questions from various input formats, eg …

We study automatic question generation for sentences from text passages in reading
comprehension. We introduce an attention-based sequence learning model for the task and …

We present a novel method for obtaining high-quality, domain-targeted multiple choice
questions from crowd workers. Generating these questions can be difficult without trading …

There has been an explosion of work in the vision & language community during the past
few years from image captioning to video transcription, and answering questions about …

Multiple-choice testing is considered one of the most effective and enduring forms of
educational assessment that remains in practice today. This study presents a …

We propose an end-to-end approach for synthetic QA data generation. Our model comprises
a single transformer-based encoder-decoder network that is trained end-to-end to generate …

We address the challenge of automatically generating questions from reading materials for
educational practice and assessment. Our approach is to overgenerate questions, then rank …

We study the task of generating from Wikipedia articles question-answer pairs that cover
content beyond a single sentence. We propose a neural network approach that incorporates …

Texts with potential educational value are becoming available through the Internet (eg,
Wikipedia, news services). However, using these new tests in classrooms introduces many …