SpaceQA: Answering Questions about the Design of Space Missions and Space Craft Concepts

TL;DR

SpaceQA is an innovative open-domain question answering system designed for space mission design, leveraging transfer learning to address domain-specific challenges and facilitate information sharing within ESA and the public.

Contribution

It introduces the first open-domain QA system for space mission design, utilizing transfer learning without fine-tuning due to limited annotated data.

Findings

Evaluation confirms the effectiveness of the retriever component.

Fine-tuning improves reading comprehension performance.

ESA is piloting SpaceQA internally.

Abstract

We present SpaceQA, to the best of our knowledge the first open-domain QA system in Space mission design. SpaceQA is part of an initiative by the European Space Agency (ESA) to facilitate the access, sharing and reuse of information about Space mission design within the agency and with the public. We adopt a state-of-the-art architecture consisting of a dense retriever and a neural reader and opt for an approach based on transfer learning rather than fine-tuning due to the lack of domain-specific annotated data. Our evaluation on a test set produced by ESA is largely consistent with the results originally reported by the evaluated retrievers and confirms the need of fine tuning for reading comprehension. As of writing this paper, ESA is piloting SpaceQA internally.