Knowledge Base Question Answering for Space Debris Queries

Autor:	Darm, Paul, Miceli-Barone, Antonio Valerio, Cohen, Shay B., Riccardi, Annalisa
Rok vydání:	2023
Předmět:	Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Databases I.2.7
Druh dokumentu:	Working Paper
Popis:	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{https://github.com/PaulDrm/DISCOSQA}. Comment: 7 pages, ACL 2023 industry track
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.19734 Zobrazit plný text záznamu View this record from Arxiv