A Neural Network Model of Metaphor Understanding with Dynamic Interaction Based on a Statistical Language Analysis

  • Asuka Terai
  • Masanori Nakagawa
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4131)


The purpose of this study is to construct a human-like neural network model that represents the process of metaphor understanding with dynamic interaction, based on data obtained from statistical language analysis. In this paper, the probabilistic relationships between concepts and their attribute values are first computed from the statistical analysis of language data. Secondly, a computational model of the metaphor understanding process is constructed, including dynamic interaction among attribute values. Finally, a psychological experiment is conducted to examine the psychological validity of the model.


Conditional Probability Neural Network Model Dynamic Interaction Latent Semantic Analysis Psychological Experiment 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ortony, A.: Beyond Literal Similarity. Psychological Review 86(3), 161–180 (1979)CrossRefGoogle Scholar
  2. 2.
    Kusumi, T.: Hiyu no Syori Katei to Imikozo. Kazama Syobo (1995)Google Scholar
  3. 3.
    Iwayama, M., Tokunaga, T., Tanaka, H.: The role of Salience in understanding Metaphors. Journal of the Japanese Society for Artificial Intelligence 6(5), 674–681 (1991)Google Scholar
  4. 4.
    Nueckles, M., Janetzko, D.: The role of semantic similarity in the comprehension of metaphor. In: Proceeding of the 19th Annual Conference of the Cognitive Science Society, pp. 578–583 (1997)Google Scholar
  5. 5.
    Gineste, M., Indurkhya, B., Scart, V.: Emergence of features in metaphor comprehension. Metaphor and Symbol 15(3), 117–135 (2000)CrossRefGoogle Scholar
  6. 6.
    Utsumi, A.: Hiyu no ninchi / Keisan Moderu. Computer Today 96(3), 34–39 (2000)Google Scholar
  7. 7.
    Nakagawa, M., Terai, A., Hirose, S.: A Neural Network Model of Metaphor Understanding. In: Proceedings of Eighth International Conference on Cognitive and Neural Systems, p. 32 (2004)Google Scholar
  8. 8.
    Pereira, F., Tishby, N., Lee, L.: Distributional clustering of English words. In: Proceedings of the 31st Meeting of the Association for Computational Linguistics, pp. 183–190 (1993)Google Scholar
  9. 9.
    Hofmann, T.: Probabilistic latent semantic indexing. In: Proceedings of the 22nd International Conference on Research and Development in Information Retrieval:SIGIR f99, pp. 50–57 (1999)Google Scholar
  10. 10.
    Kameya, Y., Sato, T.: Computation of probabilistic relationship between concepts and their attributes using a statistical analysis of Japanese corpora. In: Proceedings of Symposium on Large-scale Knowledge Resources: LKR 2005, pp. 65–68 (2005)Google Scholar
  11. 11.
    Deerwester, S., Dumais, S., Furnas, G., Landauer, T., Harshman, R.: Indexing by Latent Semantic Analysis. Journal of the Society for Information Science 41(6), 391–407 (1990)CrossRefGoogle Scholar
  12. 12.
    Kudoh, T., Matsumoto, Y.: Japanese Dependency Analysis using Cascaded Chunking. In: Proceedings of the 6th Conference on Natural Language Learning: CoNLL 2002, pp. 63–69 (2002)Google Scholar
  13. 13.
    The National Institute for Japanese Language: Word List by Semantic Principles, Revised and Enlarged Edition, Dainippon-Tosho (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Asuka Terai
    • 1
  • Masanori Nakagawa
    • 1
  1. 1.Tokyo Institute of TechnologyTokyoJapan

Personalised recommendations