DISCOSQA: A Knowledge Base Question Answering System for Space Debris based on Program Induction

Paul Darm, Antonio Valerio Miceli Barone, Shay B. Cohen, Annalisa Riccardi


Abstract
Space program agencies execute complex satellite operations that need to be supported by the technical knowledge contained in their extensive information systems. Knowledge Base (KB) databases are an effective way of storing and accessing such information to scale. In this work we present a system, developed for the European Space Agency, that can answer complex natural language queries, to support engineers in accessing the information contained in a KB that models the orbital space debris environment. Our system is based on a pipeline which first generates a program sketch from a natural language question, then specializes the sketch into a concrete query program with mentions of entities, attributes and relations, and finally executes the program against the database. This pipeline decomposition approach enables us to train the system by leveraging out-of-domain data and semi-synthetic data generated by GPT-3, thus reducing overfitting and shortcut learning even with limited amount of in-domain training data.
Anthology ID:
2023.acl-industry.47
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Sunayana Sitaram, Beata Beigman Klebanov, Jason D Williams
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
487–499
Language:
URL:
https://aclanthology.org/2023.acl-industry.47
DOI:
10.18653/v1/2023.acl-industry.47
Bibkey:
Cite (ACL):
Paul Darm, Antonio Valerio Miceli Barone, Shay B. Cohen, and Annalisa Riccardi. 2023. DISCOSQA: A Knowledge Base Question Answering System for Space Debris based on Program Induction. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pages 487–499, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
DISCOSQA: A Knowledge Base Question Answering System for Space Debris based on Program Induction (Darm et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-industry.47.pdf