SpaceQA: Answering Questions about the Design of Space Missions and Space Craft Concepts
This system addresses the need for accessible information sharing in space mission design for the European Space Agency and the public, but it is incremental as it applies existing methods to a new domain.
The researchers tackled the problem of open-domain question answering for space mission design by developing SpaceQA, the first such system, which uses a dense retriever and neural reader with transfer learning, achieving results consistent with existing retrievers but highlighting the need for fine-tuning in reading comprehension.
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.