A question-answering system for aircraft pilots' documentation

TL;DR

This paper introduces a question-answering system designed to help aircraft pilots access complex technical documentation through natural language interaction, improving information retrieval from manuals.

Contribution

It presents a novel multi-task approach for the QA module and a score combination method, enhancing performance on aviation documentation datasets.

Findings

Improved QA performance on Flight Crew Operating Manual dataset

Effective integration of retriever and QA scores

Enhanced natural language access to aircraft documentation

Abstract

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.