Generating Quizzes to Support Training on Quality Management and Assurance in Space Science and Engineering
Andr\'es Garc\'ia-Silva, Cristian Berr\'io, Jos\'e Manuel, G\'omez-P\'erez

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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSemantic Web and Ontologies · Service-Oriented Architecture and Web Services · Natural Language Processing Techniques
MethodsGated Linear Unit · Multi-Head Attention · Attention Is All You Need · Linear Layer · Weight Decay · Linear Warmup With Linear Decay · Adafactor · Attention Dropout · Adam · WordPiece
