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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Space agencies execute complex satellite operations that need to be supported by the technical knowledge contained in their extensive information systems. Knowledge bases (KB) are an effective way of storing and accessing such information at scale. In this work we present a system, developed for the European Space Agency (ESA), 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 sequence of basic database operations, called 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. Our code can be found at \url{this https URL}.
Original languageEnglish
Title of host publicationProceedings of the 61st Annual Meeting of the Association for Computational Linguistics
Subtitle of host publicationIndustry Track
PublisherAssociation for Computational Linguistics
Pages487–499
Number of pages7
Volume5
ISBN (Electronic)9781959429685
Publication statusPublished - 9 Jul 2023
Event61st Annual Meeting of the Association for Computational Linguistics - Toronto, Canada
Duration: 9 Jul 202314 Jul 2023
Conference number: 61
https://2023.aclweb.org/

Conference

Conference61st Annual Meeting of the Association for Computational Linguistics
Abbreviated titleACL 2023
Country/TerritoryCanada
CityToronto
Period9/07/2314/07/23
Internet address

Fingerprint

Dive into the research topics of 'DISCOSQA: A Knowledge Base Question Answering System for Space Debris based on Program Induction'. Together they form a unique fingerprint.

Cite this