Generating Varied Narrative Probability Exercises

This paper presents Genpex, a system for automatic generation of narrative probability exercises. Generation of exercises in Genpex is done in two steps. First, the system creates a specification of a solvable probability problem, based on input from the user (a researcher or test developer) who selects a specific question type and a narrative context for the problem. Then, a text expressing the probability problem is generated. The user can tune the generated text by setting the values of some linguistic variation parameters. By varying the mathematical content of the exercise, its narrative context and the linguistic parameter settings, many different exercises can be produced. Here we focus on the natural language generation part of Genpex. After describing how the system works, we briefly present our first evaluation results, and discuss some aspects requiring further investigation.