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

Andres Garcia-Silva, Cristian Berrio Aroca, Jose Manuel Gomez-Perez, Jose Martinez, Patrick Fleith, Stefano Scaglioni


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.
Anthology ID:
2022.inlg-demos.2
Volume:
Proceedings of the 15th International Conference on Natural Language Generation: System Demonstrations
Month:
July
Year:
2022
Address:
Waterville, Maine, USA and virtual meeting
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
4–6
Language:
URL:
https://aclanthology.org/2022.inlg-demos.2
DOI:
Bibkey:
Cite (ACL):
Andres Garcia-Silva, Cristian Berrio Aroca, Jose Manuel Gomez-Perez, Jose Martinez, Patrick Fleith, and Stefano Scaglioni. 2022. Generating Quizzes to Support Training on Quality Management and Assurance in Space Science and Engineering. In Proceedings of the 15th International Conference on Natural Language Generation: System Demonstrations, pages 4–6, Waterville, Maine, USA and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
Generating Quizzes to Support Training on Quality Management and Assurance in Space Science and Engineering (Garcia-Silva et al., INLG 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.inlg-demos.2.pdf
Software:
 2022.inlg-demos.2.software.zip