Multilingual Question Answering Systems for Knowledge Graphs—A Survey

Tracking #: 3633-4847

Authors: 
Aleksandr Perevalov
Andreas Both
Axel-Cyrille Ngonga Ngomo

Responsible editor: 
Philipp Cimiano

Submission type: 
Survey Article
Abstract: 
This paper presents a survey on 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.), thoroughly analyzing the information, searching for novel insights, and methodically organizing them. Our insights are derived from 46 publications: 25 papers specifically focused on mKGQA systems, 14 papers concerning benchmarks and datasets, and 7 systematic survey articles. Starting its search from 2011, this work presents a comprehensive overview of the research field, encompassing the most recent findings pertaining to mKGQA and Large Language Models. We categorize the acquired information into a well-defined taxonomy, which classifies the methods employed in the development of mKGQA systems. Moreover, we formally define three pivotal characteristics of these methods, namely resource efficiency, multilinguality, and portability. These formal definitions serve as crucial reference points for selecting an appropriate method for mKGQA in a given use case. Lastly, we delve into the challenges of mKGQA, offer a broad outlook on the investigated research field, and outline important directions for future research. Accompanying this paper, we provide all the collected data, scripts, and documentation in an online appendix.
Full PDF Version: 
Tags: 
Reviewed

Decision/Status: 
Accept

Solicited Reviews:
Click to Expand/Collapse
Review #1
By Hugo Gonçalo Oliveira submitted on 13/Apr/2024
Suggestion:
Accept
Review Comment:

Most of the issues pointed out in my previous revision were addressed, and I the paper is now closer to a publishable version.

On the suggested dimensions for the review, the paper:
(1) Is suitable as an introductory text;
(2) Is comprehensive and has a balanced coverage;
(3) Is well-written;
(4) Covers material that is important for, and not limited to, the Semantic Web community.

I still feel like the authors could have done more in Sec. 4, which is still very long and not clearly structured around Table 4. Nevertheless, it is more structured and slightly better connected now.
Also, despite the authors response, I still have doubts on the claims that the adopted procedure is reproducible.

Besides that, Figure 1 was complemented, Sec 4.3 was restructured, and new pertinent information was added to Sec. 4.6.

There were minor changes in Sec. 5.1. The style is still not much different from Sec 4.1, but it is not so long and it is complemented by the analysis in Sec. 5.2, which now mentions some datasets.

Sec 6 now contains some links to the surveyed systems and datasets.

Sec 7 now includes answers to the research questions.

One minor suggestion, in Sec 6.1.4, is to remove the word "from" before citation [96].

Review #2
Anonymous submitted on 07/May/2024
Suggestion:
Accept
Review Comment:

As I had no comments to the authors in the previous review round either, I am happy for the paper to be accepted as is.