Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-29351| Publication type: | Conference paper |
| Type of review: | Peer review (publication) |
| Title: | Spider4SPARQL : a complex benchmark for evaluating knowledge graph question answering systems |
| Authors: | Kosten, Catherine Cudré-Mauroux, Philippe Stockinger, Kurt |
| et. al: | No |
| DOI: | 10.1109/BigData59044.2023.10386182 10.21256/zhaw-29351 |
| Proceedings: | 2023 IEEE International Conference on Big Data (BigData) |
| Conference details: | IEEE International Conference on Big Data, Sorrento, Italy, 15-18 December 2023 |
| Issue Date: | 22-Jan-2024 |
| Publisher / Ed. Institution: | IEEE |
| ISBN: | 979-8-3503-2445-7 |
| Language: | English |
| Subjects: | Knowledge graph; Machine learning; Natural language processing; Benchmark |
| Subject (DDC): | 005: Computer programming, programs and data 006: Special computer methods |
| Abstract: | With the recent spike in the number and availability of Large Language Models (LLMs), it has become increasingly important to provide large and realistic benchmarks for evaluating Knowledge Graph Question Answering (KBQA) systems. So far the majority of benchmarks rely on pattern-based SPARQL query generation approaches. The subsequent natural language (NL) question generation is conducted through crowdsourcing or other automated methods, such as rule-based paraphrasing or NL question templates. Although some of these datasets are of considerable size, their pitfall lies in their pattern-based generation approaches, which do not always generalize well to the vague and linguistically diverse questions asked by humans in real-world contexts. In this paper, we introduce Spider4SPARQL - a new SPARQL benchmark dataset featuring 9,693 previously existing manually generated NL questions and 4,721 unique, novel, and complex SPARQL queries of varying complexity. In addition to the NL/SPARQL pairs, we also provide their corresponding 166 knowledge graphs and ontologies, which cover 138 different domains. Our complex benchmark enables novel ways of evaluating the strengths and weaknesses of modern KGQA systems. We evaluate the system with state-of-the-art KGQA systems as well as LLMs, which achieve only up to 45% execution accuracy, demonstrating that Spider4SPARQL is a challenging benchmark for future research. |
| URI: | https://digitalcollection.zhaw.ch/handle/11475/29351 |
| Fulltext version: | Accepted version |
| License (according to publishing contract): | Licence according to publishing contract |
| Departement: | School of Engineering |
| Organisational Unit: | Institute of Computer Science (InIT) |
| Published as part of the ZHAW project: | INODE – Intelligent Open Data Exploration (EU Horizon 2020) |
| Appears in collections: | Publikationen School of Engineering |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 2023_Kosten-etal_Spider4SPARQL_IEEE_BigData_2023.pdf | Accepted Version | 317.49 kB | Adobe PDF |  View/Open |
Show full item record
Kosten, C., Cudré-Mauroux, P., & Stockinger, K. (2024, January 22). Spider4SPARQL : a complex benchmark for evaluating knowledge graph question answering systems. 2023 IEEE International Conference on Big Data (BigData). https://doi.org/10.1109/BigData59044.2023.10386182
Kosten, C., Cudré-Mauroux, P. and Stockinger, K. (2024) ‘Spider4SPARQL : a complex benchmark for evaluating knowledge graph question answering systems’, in 2023 IEEE International Conference on Big Data (BigData). IEEE. Available at: https://doi.org/10.1109/BigData59044.2023.10386182.
C. Kosten, P. Cudré-Mauroux, and K. Stockinger, “Spider4SPARQL : a complex benchmark for evaluating knowledge graph question answering systems,” in 2023 IEEE International Conference on Big Data (BigData), Jan. 2024. doi: 10.1109/BigData59044.2023.10386182.
KOSTEN, Catherine, Philippe CUDRÉ-MAUROUX und Kurt STOCKINGER, 2024. Spider4SPARQL : a complex benchmark for evaluating knowledge graph question answering systems. In: 2023 IEEE International Conference on Big Data (BigData). Conference paper. IEEE. 22 Januar 2024. ISBN 979-8-3503-2445-7
Kosten, Catherine, Philippe Cudré-Mauroux, and Kurt Stockinger. 2024. “Spider4SPARQL : A Complex Benchmark for Evaluating Knowledge Graph Question Answering Systems.” Conference paper. In 2023 IEEE International Conference on Big Data (BigData). IEEE. https://doi.org/10.1109/BigData59044.2023.10386182.
Kosten, Catherine, et al. “Spider4SPARQL : A Complex Benchmark for Evaluating Knowledge Graph Question Answering Systems.” 2023 IEEE International Conference on Big Data (BigData), IEEE, 2024, https://doi.org/10.1109/BigData59044.2023.10386182.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.