Multilingual Question Answering Systems for Knowledge Graphs—A Survey

This paper presents a systematic survey of the research field of multilingual Knowledge Graph Question Answering (mKGQA). We employ a systematic review methodology to collect and analyze the research results in the field of mKGQA by defining scientific literature sources, selecting relevant publications, extracting objective information (e.g., problem, approach, evaluation values, used metrics, etc.), analyzing the information, searching for new insights as well as generalizing them in a structured manner. Our insights are mainly derived from 37 publications: 21 papers about mKGQA systems, 9 papers about benchmarks and datasets, and 7 systematic survey articles. This work introduces a taxonomy for the methods used or the development of mKGQA systems. In addition, we formally define three major characteristics of these methods: resource efficiency, multilinguality, and portability. The formal definitions are intended to serve as landmarks for the selection of a particular method for mKGQA in a given use case. We provide all the collected data, scripts, and documentation as an online appendix. Finally, we discuss the challenges of mKGQA, offer a general outlook on the investigated research field, and define important future research directions.