Abstract
The natural language query becomes an extension of the existing World Wide Web. Also searching the web become so difficult due to the huge increase of the unstructured data, and this leads to the increase of knowledge needed to be captured/answered from the available data. Furthermore, many proposed systems had been introduced to get relevant and accurate answers to the given natural language queries. In this paper a new proposed model will be introduced, which includes ontology, and applied NLP algorithms that are capable to generate query graphs and enhancing the conversion of paragraphs into triples form. The answers are based on large paragraphs and any types of complex questions. Moreover, we used Stanford CoreNLP for converting sentences into the form of triples. The used dataset is Stanford SQuAD dataset. The output results show relevant data with an accuracy of 82.27%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ahmed, K., Yasser, O., Atef, G.: Simultaneous mapping of multi RDB to RDF. In: The 7th International Conference on Computer Science and Information Technology (CSIT), pp. 1–5 (2016). https://doi.org/10.1109/CSIT.2016.7549455
Yasser, O., Ahmed, A.M., Kamal, M.: Building a framework for mapping RDBMS to RDF with semantic query capabilities. In: The 60th International Scientific Conference on Information Technology and Management Science of Riga Technical University (ITMS), pp. 1–5 (2019). https://doi.org/10.1109/ITMS47855.2019.8940733
Umang, M., Devashri, S., Aditi, P., Safa, H.: Natural language processing based text summarization and querying model. In: The Fourth International Conference on Inventive Systems and Control (ICISC), pp. 806–810 (2020). https://doi.org/10.1109/ICISC47916.2020.9171068
Renzo, A., Harsh, T., Dominik, T.: Mapping RDF databases to property graph databases. In: IEEE Access, vol. 8, pp. 86091–86110 (2020). https://doi.org/10.1109/ACCESS.2020.2993117
SPARQL Query Language for RDF. W3.org (2013). https://www.w3.org/TR/rdf-sparql-query/. Accessed 20 May 2022
Mattia, S., Maurizio, A.: SPARQL queries over source code. In: IEEE Tenth International Conference on Semantic Computing (ICSC), pp. 104–106 (2016). https://doi.org/10.1109/ICSC.2016.65
Yael A., Yehuda, C.: SPARQLIt: interactive SPARQL query refinement. In: IEEE 37th International Conference on Data Engineering (ICDE), pp. 2649–2652 (2021). https://doi.org/10.1109/ICDE51399.2021.00295
Stanford NLP Group | Software Summary. Stanfordnlp.github.io. https://stanfordnlp.github.io/. Accessed 20 Mar 2022
CoreNLP. 2020 Overview. https://stanfordnlp.github.io/CoreNLP/. Accessed 20 May 2022
Christopher, M., Mihai, S., John, B., Jenny, F., Steven, B., David, M.: The Stanford CoreNLP natural language processing toolkit. In: The 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, Baltimore, Maryland USA, pp. 55–60 (2014)
Haemin, J., Wooju, K.: Automated conversion from natural language query to SPARQL query. J. Intell. Inf. Syst. 55(3), 501–520 (2020)
Peter, O.: PAROT: translating natural language to SPARQL. Expert Syst. Appl.: X 5, 100024 (2020)
Mickael, R., Rim, H., Sarra, B.A., Philippe, C.: Hybrid question answering system based on natural language processing and SPARQL query. In: The 3rd International Workshop on the Applications of Knowledge Representation and Semantic Technologies in Robotics (AnSWeR19) (2019). Researchgate. https://www.researchgate.net/publication/338067963_Hybrid_Question_Answering_System_based_on_Natural_Language_Processing_and_SPARQL_Query
Yuhao, C., Farhana, Z.: BIRD-QA: a BERT-based information retrieval approach to domain specific question answering. In: IEEE International Conference on Big Data (Big Data), pp. 3503–3510 (2021). https://doi.org/10.1109/BigData52589.2021.9671523
Rohit, A., Parth, S., Hemlata, G., Sunita, S., Smita, V.: Comparative question answering system based on natural language processing and machine learning. In: The International Conference on Artificial Intelligence and Smart Systems (ICAIS), pp. 373–378 (2021). https://doi.org/10.1109/ICAIS50930.2021.9396015
The Stanford Question Answering Dataset. Rajpurkar.github.io. https://rajpurkar.github.io/SQuAD-explorer/. Accessed 20 Jan 2021
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Nageeb, A.A., Mahmoud, A.S., Omar, Y.K. (2023). An Approach for Building a Framework for Applying Natural Language Queries on RDF Database. In: Hassanien, A.E., Snášel, V., Tang, M., Sung, TW., Chang, KC. (eds) Proceedings of the 8th International Conference on Advanced Intelligent Systems and Informatics 2022. AISI 2022. Lecture Notes on Data Engineering and Communications Technologies, vol 152. Springer, Cham. https://doi.org/10.1007/978-3-031-20601-6_51
Download citation
DOI: https://doi.org/10.1007/978-3-031-20601-6_51
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20600-9
Online ISBN: 978-3-031-20601-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)