Girish Kumar

RevUP: Automatically Generating Questions from Educational Texts

Girish Kumar, Singapore Finalist, 16-18

The continued crafting of varied recall and application questions can be extremely time and resource intensive for teachers. That’s why I built RevUP, which AUTOMATICALLY generates gap-fill multiple choice questions from online texts, such as the one below: 1. Endocrine signals generated by the hypothalamus regulate hormone secretion by the ____. (a) posterior pituitary (b) anterior pituitary (c) thyroid gland (d) pineal gland RevUP factors the problem of generating good questions into 3 parts: 1) Selecting topically important sentences to ask about 2) Identifying which part of the resulting sentence to choose as the gap 3) Crafting effective distractors to be part of the set of options to confuse the learner RevUP builds upon and proposes accurate techniques spanning the fields of AI, Machine Learning and Natural Language Processing to solve each of the problems above.