Knowledge Base Question Answering for Space Debris Queries

May 31, 2023 Β· Declared Dead Β· πŸ› Annual Meeting of the Association for Computational Linguistics

πŸ’€ CAUSE OF DEATH: 404 Not Found
Code link is broken/dead
Authors Paul Darm, Antonio Valerio Miceli-Barone, Shay B. Cohen, Annalisa Riccardi arXiv ID 2305.19734 Category cs.AI: Artificial Intelligence Cross-listed cs.CL, cs.DB Citations 1 Venue Annual Meeting of the Association for Computational Linguistics Repository https://github.com/PaulDrm/DISCOSQA} Last Checked 1 month ago
Abstract
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}.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence

Died the same way β€” πŸ’€ 404 Not Found