English

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

Computation and Language 2022-11-07 v2 Artificial Intelligence

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.

Keywords

Cite

@article{arxiv.2210.03427,
  title  = {Generating Quizzes to Support Training on Quality Management and Assurance in Space Science and Engineering},
  author = {Andrés García-Silva and Cristian Berrío and José Manuel Gómez-Pérez},
  journal= {arXiv preprint arXiv:2210.03427},
  year   = {2022}
}

Comments

In Proceedings of the 15th International Natural Language Generation Conference (INLG 2022)