Development of a Semantic and Syntactic Model of Natural Language by Means of Non-negative Matrix and Tensor Factorization

  • Anatoly Anisimov
  • Oleksandr Marchenko
  • Volodymyr Taranukha
  • Taras Vozniuk
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8655)


A method for developing a structural model of natural language syntax and semantics is proposed. Syntactic and semantic relations between parts of a sentence are presented in the form of a recursive structure called a control space. Numerical characteristics of these data are stored in multidimensional arrays. After factorization, the arrays serve as the basis for the development of procedures for analyses of natural language semantics and syntax.


Information Extraction WordNet Wikipedia Knowledge Representation Ontologies 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Van de Cruys, T.: A Non-negative Tensor Factorization Model for Selectional Preference Induction. Journal of Natural Language Engineering 16(4), 417–437 (2010)CrossRefGoogle Scholar
  2. 2.
    Van de Cruys, T., Rimell, L., Poibeau, T., Korhonen, A.: Multi-way Tensor Factorization for Unsupervised Lexical Acquisition. In: Proceedings of COLING 2012, pp. 2703–2720 (2012)Google Scholar
  3. 3.
    Cohen, S.B., Collins, M.: Tensor Decomposition for Fast Parsing with Latent-Variable PCFGs. In: NIPS 2012, pp. 2528–2536 (2012)Google Scholar
  4. 4.
    Wei, P., Tao, L.: On the equivalence between nonnegative tensor factorization and tensorial probabilistic latent semantic analysis. Applied Intelligence, Springer Journals 35(2), 285–295 (2011)Google Scholar
  5. 5.
    Anisimov, A.V.: Control space of syntactic structures of natural language. Cybernetics and System Analysis 93, 11–17 (1990)Google Scholar
  6. 6.
    Chomsky, N.: Syntactic Structures, 117 p. Mouton & Co. (1957)Google Scholar
  7. 7.
    Tesnière, L.: Èlèments de syntaxe structurale. Klincksieck, Paris (1959)Google Scholar
  8. 8.
    Klein, D., Manning, C.D.: Accurate Unlexicalized Parsing. In: Proceedings of ACL 2003, pp. 423–430 (2003)Google Scholar
  9. 9.
    de Marneffe, M.-C., MacCartney, B., Manning, C.D.: Generating Typed Dependency Parses from Phrase Structure Parses. In: Proceedings of LREC (2006),
  10. 10.
    Lee, D.D., Seung, H.S.: Algorithms for Non-Negative Matrix Factorization. In: NIPS (2000),
  11. 11.
    Cichocki, A., Zdunek, R., Phan, A.-H., Amari, S.-I.: Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation. J. Wiley & Sons, Chichester (2009)CrossRefGoogle Scholar
  12. 12.
    Kasami, T.: An efficient recognition and syntax-analysis algorithm for context-free languages. Scientific report AFCRL-65-758. Air Force Cambridge Research Lab, Bedford, MA (1965)Google Scholar
  13. 13.
    Deerwester, S., Dumais, S.T., Furnas, G.W., Landauer, T.K., Harshman, R.: Indexing by Latent Semantic Analysis. Journal of the American Society for Information Science 41(6), 391–407 (1990)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Anatoly Anisimov
    • 1
  • Oleksandr Marchenko
    • 1
  • Volodymyr Taranukha
    • 1
  • Taras Vozniuk
    • 1
  1. 1.Faculty of CyberneticsTaras Shevchenko National University of KyivUkraine

Personalised recommendations