Skip to main content
Springer Nature Link
Log in

Missing Types Prediction in Linked Data Using Deep Neural Network with Attention Mechanism: Case Study on DBpedia and UniProt Datasets

  • Conference paper
  • First Online:
Information Technology for Management: Approaches to Improving Business and Society (FedCSIS-AIST 2022, ISM 2022)

Part of the book series: Lecture Notes in Business Information Processing ((LNBIP,volume 471))

  • 193 Accesses

Abstract

The publication and use of linked data in various fields has become commonplace. However, data published under the linked data principles suffer from issues such as uncertainty, incompleteness, imprecision, etc. We distinguish the problem of missing types for RDF entities among the causes of data incompleteness. In this paper, we propose a deep learning approach for detecting missing types. Our approach consists of using an encoder-decoder model with an attention mechanism, in which we use embedding layers to improve data representation and GRU cells to increase efficiency when processing the different sequences in input and output. The main goal of this work is to improve the quality of the literature results and to take into account the various triples in order to detect the correct type for each entity. This allows us to detect the types of entities and thus deduce other connections with other entities. As a result, we will be able to address a portion of the problem of incompleteness, allowing the various applications that use this data to produce more relevant results. This work only considers types. The other semantic links between entities are not considered. We conducted a case study on the UniProt dataset to evaluate the quality of our approach, which is a large database of protein sequences and annotations. We used our model to generate the missing types in two datasets: DBpedia and UniProt. The effectiveness of our approach has been demonstrated by the evaluation results.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://www.w3.org/.

  2. 2.

    https://colab.research.google.com/.

  3. 3.

    http://gaia.infor.uva.es/hdt/dbpedia2016-10/dbpedia2016-10.hdt.

  4. 4.

    https://www.uniprot.org/help/downloads.

References

  1. Barati, M., Bai, Q., Liu, Q.: An entropy-based class assignment detection approach for RDF data. In: Geng, X., Kang, B.-H. (eds.) PRICAI 2018. LNCS (LNAI), vol. 11013, pp. 412–420. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-97310-4_47

    Chapter  Google Scholar 

  2. Berners-Lee, T.: Linked data - design issues. https://www.w3.org/DesignIssues/LinkedData.html (2006). Accessed 09 May 2022

  3. Berners-Lee, T., Hendler, J., Lassila, O.: The semantic web. Scientific Am. 284(5), 34–43 (2001). https://www.sciam.com/article.cfm?articleID=00048144-10D2-1C70-84A9809EC588EF21

  4. Biswas, R., Sofronova, R., Alam, M., Sack, H.: Entity type prediction in knowledge graphs using embeddings. arXiv preprint arXiv:2004.13702 (2020)

  5. Biswas, R., Türker, R., Moghaddam, F.B., Koutraki, M., Sack, H.: Wikipedia infobox type prediction using embeddings. In: DL4KGS@ ESWC, pp. 46–55 (2018)

    Google Scholar 

  6. Bizer, C., Heath, T., Berners-Lee, T.: Linked data: the story so far. In: Sheth, A. (ed.) Semantic Services, Interoperability and Web Applications: Emerging Concepts, pp. 205–227. IGI Global (2011). https://doi.org/10.4018/978-1-60960-593-3.ch008

  7. Craswell, N.: Mean reciprocal rank. In: Liu, L., Özsu, M.T. (eds.) Encyclopedia of Database Systems, p. 1703. Springer, Boston (2009). https://doi.org/10.1007/978-0-387-39940-9_488

  8. Du, J., Chen, Q., Peng, Y., Xiang, Y., Tao, C., Lu, Z.: ML-Net: multi-label classification of biomedical texts with deep neural networks. J. Am. Med. Inform. Assoc. 26(11), 1279–1285 (2019). https://doi.org/10.1093/jamia/ocz085

    Article  Google Scholar 

  9. Fareh, M.: Modeling incomplete knowledge of semantic web using Bayesian networks. Appl. Artif. Intell. 33(11), 1022–1034 (2019)

    Article  Google Scholar 

  10. Fiorini, R.A.: Computational intelligence from autonomous system to super-smart society and beyond. Int. J. Softw. Sci. Comput. Intell. (IJSSCI) 12(3), 1–13 (2020). https://doi.org/10.4018/IJSSCI.2020070101

    Article  Google Scholar 

  11. Hamel, O., Fareh, M.: Encoder-decoder neural network with attention mechanism for types detection in linked data. In: 2022 17th Conference on Computer Science and Intelligence Systems (FedCSIS), pp. 733–739. IEEE (2022)

    Google Scholar 

  12. Jin, H., Li, C., Zhang, J., Hou, L., Li, J., Zhang, P.: Xlore2: large-scale cross-lingual knowledge graph construction and application. Data Intell. 1(1), 77–98 (2019). https://doi.org/10.1162/dint_a_00003

    Article  Google Scholar 

  13. Kliegr, T., Zamazal, O.: LHD 2.0: a text mining approach to typing entities in knowledge graphs. J. Web Semant. 39, 47–61 (2016)

    Google Scholar 

  14. Kondratyeva, L., Alekseenko, I., Chernov, I., Sverdlov, E.: Data incompleteness may form a hard-to-overcome barrier to decoding life’s mechanism. Biology 11(8), 1208 (2022)

    Article  Google Scholar 

  15. Laskey, K.J., Laskey, K.B.: Uncertainty reasoning for the world wide web: Report on the urw3-XG incubator group. URSW 8, 108–116 (2008)

    MathSciNet  Google Scholar 

  16. Mihindukulasooriya, N., Rico, M.: Type prediction of RDE knowledge graphs using binary classifiers with structural data. In: Pautasso, C., Sánchez-Figueroa, F., Systä, K., Murillo Rodríguez, J.M. (eds.) ICWE 2018. LNCS, vol. 11153, pp. 279–287. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-03056-8_27

    Chapter  Google Scholar 

  17. Nagy, A., et al.: Identification and correction of abnormal, incomplete and mispredicted proteins in public databases. BMC Bioinform. 9(1), 1–26 (2008)

    Article  Google Scholar 

  18. Nechaev, Y., Corcoglioniti, F., Giuliano, C.: Type prediction combining linked open data and social media. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pp. 1033–1042 (2018). https://doi.org/10.1145/3269206.3271781

  19. Paulheim, H., Bizer, C.: Type inference on noisy RDF data. In: Alani, H., et al. (eds.) ISWC 2013. LNCS, vol. 8218, pp. 510–525. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-41335-3_32

    Chapter  Google Scholar 

  20. Riali, I., Fareh, M., Ibnaissa, M.C., Bellil, M.: A semantic-based approach for hepatitis c virus prediction and diagnosis using a fuzzy ontology and a fuzzy bayesian network. J. Intell. Fuzzy Syst. 44, 1–15 (2022)

    Google Scholar 

  21. Ristoski, P., Paulheim, H.: Semantic web in data mining and knowledge discovery: a comprehensive survey. J. Web Semantics 36, 1–22 (2016). https://doi.org/10.1016/j.websem.2016.01.001

    Article  Google Scholar 

  22. Sumba, X., Ortiz, J.: Between the interaction of graph neural networks and semantic web. In: Proceedings of the 2019 NeurIPS Workshop on Graph Representation Learning (2019)

    Google Scholar 

  23. Wilcox, C., Djahel, S., Giagos, V.: Identifying the main causes of medical data incompleteness in the smart healthcare era. In: 2021 International Symposium on Networks, Computers and Communications (ISNCC), pp. 1–6. IEEE (2021)

    Google Scholar 

  24. Zhang, M.L., Zhou, Z.H.: A review on multi-label learning algorithms. IEEE Trans. Knowl. Data Eng. 26(8), 1819–1837 (2013). https://doi.org/10.1109/TKDE.2013.39

    Article  Google Scholar 

  25. Zhang, X., Lin, E., Pi, S.: Predicting object types in linked data by text classification. In: 2017 Fifth International Conference on Advanced Cloud and Big Data (CBD), pp. 391–396. IEEE (2017). https://doi.org/10.1109/CBD.2017.74

Download references

Author information

Authors and Affiliations

  1. LRDSI Laboratory, Faculty of Sciences, University Blida 1, B.P 270, Route de Soumaa, Blida, Algeria

    Oussama Hamel & Messaouda Fareh

Authors
  1. Oussama Hamel
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Messaouda Fareh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Oussama Hamel .

Editor information

Editors and Affiliations

  1. University of Economics in Katowice, Katowice, Poland

    Ewa Ziemba

  2. University of Warsaw, Warsaw, Poland

    Witold Chmielarz

  3. University of Szczecin, Szczecin, Poland

    Jarosław Wątróbski

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Hamel, O., Fareh, M. (2023). Missing Types Prediction in Linked Data Using Deep Neural Network with Attention Mechanism: Case Study on DBpedia and UniProt Datasets. In: Ziemba, E., Chmielarz, W., Wątróbski, J. (eds) Information Technology for Management: Approaches to Improving Business and Society. FedCSIS-AIST ISM 2022 2022. Lecture Notes in Business Information Processing, vol 471. Springer, Cham. https://doi.org/10.1007/978-3-031-29570-6_11

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-29570-6_11

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-29569-0

  • Online ISBN: 978-3-031-29570-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics