Comparison of Two Versions of Formalization Method for Text Expressed Knowledge

  • Martina Asenbrener Katic
  • Sanja Candrlic
  • Mile Pavlic
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 716)

Abstract

The Node of Knowledge (NOK) method is a method for knowledge representation. It is used as a basis for development of formalism for textual knowledge representation (FNOK). Two versions of formalization methods and, respectively, two Question Answering (QA) systems are developed. The first system uses grammars; it is written and implemented in Python. The second, improved system is based on storing text in relational databases without losing semantics and it is implemented in Oracle.

This paper presents the results of comparison of the two QA systems. The first system was tested using 42 sentences. It received 88 questions from users and provided answers. After improving the formalization method, the second system was tested with the same set of sentences and questions. The paper presents the results of the testing, the comparison of answers received from both systems and the analysis of correctness of the answers received.

Keywords

NOK Node of Knowledge Relational database Question answering systems Knowledge Knowledge-based systems 

References

  1. 1.
    Asenbrener Katic, M., Pavlic, M., Candrlic, S.: The representation of database content and structure using the NOK method. Procedia Eng. 100, 1075–1081 (2015)CrossRefGoogle Scholar
  2. 2.
    Hirschman, L., Gaizauskas, R.: Natural language question answering: the view from here. Nat. Lang. Eng. 7, 275–300 (2001)CrossRefGoogle Scholar
  3. 3.
    Jach, T., Xięski, T.: Inference in expert systems using natural language processing. In: Kozielski, S., Mrozek, D., Kasprowski, P., Małysiak-Mrozek, B., Kostrzewa, D. (eds.) BDAS 2015. CCIS, vol. 521, pp. 288–298. Springer, Cham (2015). doi:10.1007/978-3-319-18422-7_26 Google Scholar
  4. 4.
    Jakupovic, A., Pavlic, M., Han, Z.D.: Formalisation method for the text expressed knowledge. Expert Syst. Appl. 41, 5308–5322 (2014)CrossRefGoogle Scholar
  5. 5.
    Jakupovic, A., Pavlic, M., Mestrovic, A., Jovanovic, V.: Comparison of the nodes of knowledge method with other graphical methods for knowledge representation. In: Proceedings of the 36th International Convention CIS MIPRO, pp. 1276–1280 (2013)Google Scholar
  6. 6.
    Kovács, L.: SQL generation for natural language interface. J. Comput. Sci. Control Syst. 2(18), 19–22 (2009)Google Scholar
  7. 7.
    Kumova, Bİ.: Generating ontologies from relational data with fuzzy-syllogistic reasoning. In: Kozielski, S., Mrozek, D., Kasprowski, P., Małysiak-Mrozek, B., Kostrzewa, D. (eds.) BDAS 2015. CCIS, vol. 521, pp. 21–32. Springer, Cham (2015). doi:10.1007/978-3-319-18422-7_2 Google Scholar
  8. 8.
    Mollá, D., Vicedo, J.L.: Question answering in restricted domains: an overview. Comput. Linguist. 33, 41–61 (2007)CrossRefGoogle Scholar
  9. 9.
    Oracle: SQL- the natural language for analysis, Oracle White Paper (2015)Google Scholar
  10. 10.
    Pavlic, M.: Informacijski sustavi (Information systems). Skolska knjiga, Zagreb (2011)Google Scholar
  11. 11.
    Pavlic, M.: Oblikovanje baza podataka (Database design). Odjel za informatiku, Sveuciliste u Rijeci (2011)Google Scholar
  12. 12.
    Pavlic, M., Dovedan Han, Z., Jakupovic, A.: Question answering with a conceptual framework for knowledge-based system development ‘node of knowledge’. Expert Syst. Appl. 42, 5264–5286 (2015)CrossRefGoogle Scholar
  13. 13.
    Pavlic, M., Jakupovic, A., Mestrovic, A.: Nodes of knowledge method for knowledge representation. Informatologia 46, 206–214 (2013)Google Scholar
  14. 14.
    Pavlic, M., Mestrovic, A., Jakupovic, A.: Graph-based formalisms for knowledge representation. In: Proceedings of the 17th World Multi-Conference on Systemic Cybernetics and Informatics WMSCI, pp. 200–204 (2013)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Martina Asenbrener Katic
    • 1
  • Sanja Candrlic
    • 1
  • Mile Pavlic
    • 1
  1. 1.Department of InformaticsUniversity of RijekaRijekaCroatia

Personalised recommendations