A Domain-Specific Question-Answering System for Railway Data: A Hybrid Approach

Both, Andreas

doi:10.1007/978-3-031-99554-5_45

A Domain-Specific Question-Answering System for Railway Data: A Hybrid Approach

2026-01-01

0

PRE

AI

B

Both, Andreas *

H

Herbst, Kai

K

Krieg, Rene

L

Landmann, Magdalena

A

Alef, Martin Raphael

D

Diettrich, Anton

DOI：10.1007/978-3-031-99554-5_45

Original

Original request for help

Save

Abstract

En 中文

This paper presents insights into a real-world railway ontology and a corresponding Knowledge Graph Question Answering (KGQA) approach within the domain of train and track operations, developed in collaboration with DB Systel GmbH (subsidiary of the main German railway company). Our solution enables seamless access to infrastructure elements, train schedules, and operational data via a question-answering system powered by Large Language Models (LLMs). To ensure high quality, cost efficiency, and runtime performance, LLMs are utilized exclusively for SPARQL query generation, striking a balance between flexibility and control. This approach significantly enhances the precision and efficiency of information retrieval, making railway data more accessible and actionable. We discuss the implementation, evaluation results, and key trade-offs of our approach.

Keywords:

Corporate Knowledge Graph

Question Answering

Large Language Models

A Domain-Specific Question-Answering System for Railway Data: A Hybrid Approach

Abstract

Journal

Organization

Cited Papers

Citing Papers