A Comparative Study of Question Answering over Knowledge Bases
This work provides practical guidelines for selecting KBQA systems in various scenarios, though it is incremental with a focus on benchmarking and minor enhancements.
The authors conducted a comparative study of six KBQA systems across eight benchmark datasets to identify challenges and propose an advanced mapping algorithm that improves performance, while also introducing a multilingual COVID-19 corpus to support research.
Question answering over knowledge bases (KBQA) has become a popular approach to help users extract information from knowledge bases. Although several systems exist, choosing one suitable for a particular application scenario is difficult. In this article, we provide a comparative study of six representative KBQA systems on eight benchmark datasets. In that, we study various question types, properties, languages, and domains to provide insights on where existing systems struggle. On top of that, we propose an advanced mapping algorithm to aid existing models in achieving superior results. Moreover, we also develop a multilingual corpus COVID-KGQA, which encourages COVID-19 research and multilingualism for the diversity of future AI. Finally, we discuss the key findings and their implications as well as performance guidelines and some future improvements. Our source code is available at \url{https://github.com/tamlhp/kbqa}.