Generating Quizzes to Support Training on Quality Management and Assurance in Space Science and Engineering

TL;DR

This paper introduces a system that automatically generates quizzes from space quality assurance documents using advanced language models, aiming to improve training effectiveness in space science and engineering.

Contribution

It presents a novel approach combining T5, BART, and RoBERTa models to generate and verify quiz questions from domain-specific documents.

Findings

Effective question generation from space quality documents

Automated answer extraction and verification

Potential to enhance training evaluation processes

Abstract

Quality management and assurance is key for space agencies to guarantee the success of space missions, which are high-risk and extremely costly. In this paper, we present a system to generate quizzes, a common resource to evaluate the effectiveness of training sessions, from documents about quality assurance procedures in the Space domain. Our system leverages state of the art auto-regressive models like T5 and BART to generate questions, and a RoBERTa model to extract answers for such questions, thus verifying their suitability.