A question-answering system for aircraft pilots' documentation
This system addresses the challenge of efficiently accessing critical information from extensive technical documentation for aircraft pilots, aiming to improve their workflow.
This paper introduces a question-answering (QA) system designed to assist aircraft pilots in navigating complex technical documentation. The system allows pilots to query information using natural language, and a multi-task learning approach for the QA module improved performance on a Flight Crew Operating Manual (FCOM) dataset.
The aerospace industry relies on massive collections of complex and technical documents covering system descriptions, manuals or procedures. This paper presents a question answering (QA) system that would help aircraft pilots access information in this documentation by naturally interacting with the system and asking questions in natural language. After describing each module of the dialog system, we present a multi-task based approach for the QA module which enables performance improvement on a Flight Crew Operating Manual (FCOM) dataset. A method to combine scores from the retriever and the QA modules is also presented.