MST5 -- Multilingual Question Answering over Knowledge Graphs

TL;DR

This paper presents a simplified multilingual KGQA approach using a single pretrained transformer model to improve SPARQL query generation across diverse languages, demonstrated on recent datasets including Chinese and Japanese.

Contribution

It introduces a novel method that integrates auxiliary information directly into a single multilingual transformer, enhancing multilingual KGQA performance.

Findings

Improved accuracy on QALD-9-Plus and QALD-10 datasets.

Effective handling of Chinese and Japanese queries.

Outperforms existing multilingual KGQA systems.

Abstract

Knowledge Graph Question Answering (KGQA) simplifies querying vast amounts of knowledge stored in a graph-based model using natural language. However, the research has largely concentrated on English, putting non-English speakers at a disadvantage. Meanwhile, existing multilingual KGQA systems face challenges in achieving performance comparable to English systems, highlighting the difficulty of generating SPARQL queries from diverse languages. In this research, we propose a simplified approach to enhance multilingual KGQA systems by incorporating linguistic context and entity information directly into the processing pipeline of a language model. Unlike existing methods that rely on separate encoders for integrating auxiliary information, our strategy leverages a single, pretrained multilingual transformer-based language model to manage both the primary input and the auxiliary data. Our methodology significantly improves the language model's ability to accurately convert a natural language query into a relevant SPARQL query. It demonstrates promising results on the most recent QALD datasets, namely QALD-9-Plus and QALD-10. Furthermore, we introduce and evaluate our approach on Chinese and Japanese, thereby expanding the language diversity of the existing datasets.